pg_waldump: support decoding of WAL inside tarfile

From 49d74dca63e15c300a8ccf317d17003f6f9412e8 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 24 Jul 2025 16:37:43 +0530
Subject: [PATCH v2 8/9] pg_verifybackup: Rename the wal-directory switch to
 wal-path

Future patches to pg_waldump will enable it to decode WAL directly
from tar files. This means you'll be able to specify a tar archive
path instead of a traditional WAL directory.

To keep things consistent and more versatile, we should also
generalize the input switch for pg_verifybackup. It should accept
either a directory or a tar file path that contains WALs. This change
will also aligning it with the existing manifest-path switch naming.
---
 doc/src/sgml/ref/pg_verifybackup.sgml     |  2 +-
 src/bin/pg_verifybackup/pg_verifybackup.c | 22 +++++++++++-----------
 src/bin/pg_verifybackup/po/de.po          |  4 ++--
 src/bin/pg_verifybackup/po/el.po          |  4 ++--
 src/bin/pg_verifybackup/po/es.po          |  4 ++--
 src/bin/pg_verifybackup/po/fr.po          |  4 ++--
 src/bin/pg_verifybackup/po/it.po          |  4 ++--
 src/bin/pg_verifybackup/po/ja.po          |  4 ++--
 src/bin/pg_verifybackup/po/ka.po          |  4 ++--
 src/bin/pg_verifybackup/po/ko.po          |  4 ++--
 src/bin/pg_verifybackup/po/ru.po          |  4 ++--
 src/bin/pg_verifybackup/po/sv.po          |  4 ++--
 src/bin/pg_verifybackup/po/uk.po          |  4 ++--
 src/bin/pg_verifybackup/po/zh_CN.po       |  4 ++--
 src/bin/pg_verifybackup/po/zh_TW.po       |  4 ++--
 src/bin/pg_verifybackup/t/007_wal.pl      |  4 ++--
 16 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index 61c12975e4a..e9b8bfd51b1 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -261,7 +261,7 @@ PostgreSQL documentation
 
      <varlistentry>
       <term><option>-w <replaceable class="parameter">path</replaceable></option></term>
-      <term><option>--wal-directory=<replaceable class="parameter">path</replaceable></option></term>
+      <term><option>--wal-path=<replaceable class="parameter">path</replaceable></option></term>
       <listitem>
        <para>
         Try to parse WAL files stored in the specified directory, rather than
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 31ebc1581fb..1ee400199da 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -93,7 +93,7 @@ static void verify_file_checksum(verifier_context *context,
 								 uint8 *buffer);
 static void parse_required_wal(verifier_context *context,
 							   char *pg_waldump_path,
-							   char *wal_directory);
+							   char *wal_path);
 static astreamer *create_archive_verifier(verifier_context *context,
 										  char *archive_name,
 										  Oid tblspc_oid,
@@ -126,7 +126,7 @@ main(int argc, char **argv)
 		{"progress", no_argument, NULL, 'P'},
 		{"quiet", no_argument, NULL, 'q'},
 		{"skip-checksums", no_argument, NULL, 's'},
-		{"wal-directory", required_argument, NULL, 'w'},
+		{"wal-path", required_argument, NULL, 'w'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -135,7 +135,7 @@ main(int argc, char **argv)
 	char	   *manifest_path = NULL;
 	bool		no_parse_wal = false;
 	bool		quiet = false;
-	char	   *wal_directory = NULL;
+	char	   *wal_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -221,8 +221,8 @@ main(int argc, char **argv)
 				context.skip_checksums = true;
 				break;
 			case 'w':
-				wal_directory = pstrdup(optarg);
-				canonicalize_path(wal_directory);
+				wal_path = pstrdup(optarg);
+				canonicalize_path(wal_path);
 				break;
 			default:
 				/* getopt_long already emitted a complaint */
@@ -365,15 +365,15 @@ main(int argc, char **argv)
 		verify_backup_checksums(&context);
 
 	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+	if (wal_path == NULL)
+		wal_path = psprintf("%s/pg_wal", context.backup_directory);
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
 	 */
 	if (!no_parse_wal)
-		parse_required_wal(&context, pg_waldump_path, wal_directory);
+		parse_required_wal(&context, pg_waldump_path, wal_path);
 
 	/*
 	 * If everything looks OK, tell the user this, unless we were asked to
@@ -1198,7 +1198,7 @@ verify_file_checksum(verifier_context *context, manifest_file *m,
  */
 static void
 parse_required_wal(verifier_context *context, char *pg_waldump_path,
-				   char *wal_directory)
+				   char *wal_path)
 {
 	manifest_data *manifest = context->manifest;
 	manifest_wal_range *this_wal_range = manifest->first_wal_range;
@@ -1208,7 +1208,7 @@ parse_required_wal(verifier_context *context, char *pg_waldump_path,
 		char	   *pg_waldump_cmd;
 
 		pg_waldump_cmd = psprintf("\"%s\" --quiet --path=\"%s\" --timeline=%u --start=%X/%08X --end=%X/%08X\n",
-								  pg_waldump_path, wal_directory, this_wal_range->tli,
+								  pg_waldump_path, wal_path, this_wal_range->tli,
 								  LSN_FORMAT_ARGS(this_wal_range->start_lsn),
 								  LSN_FORMAT_ARGS(this_wal_range->end_lsn));
 		fflush(NULL);
@@ -1376,7 +1376,7 @@ usage(void)
 	printf(_("  -P, --progress              show progress information\n"));
 	printf(_("  -q, --quiet                 do not print any output, except for errors\n"));
 	printf(_("  -s, --skip-checksums        skip checksum verification\n"));
-	printf(_("  -w, --wal-directory=PATH    use specified path for WAL files\n"));
+	printf(_("  -w, --wal-path=PATH         use specified path for WAL files\n"));
 	printf(_("  -V, --version               output version information, then exit\n"));
 	printf(_("  -?, --help                  show this help, then exit\n"));
 	printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
diff --git a/src/bin/pg_verifybackup/po/de.po b/src/bin/pg_verifybackup/po/de.po
index a9e24931100..9b5cd5898cf 100644
--- a/src/bin/pg_verifybackup/po/de.po
+++ b/src/bin/pg_verifybackup/po/de.po
@@ -785,8 +785,8 @@ msgstr "  -s, --skip-checksums        Überprüfung der Prüfsummen überspringe
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/el.po b/src/bin/pg_verifybackup/po/el.po
index 3e3f20c67c5..81442f51c17 100644
--- a/src/bin/pg_verifybackup/po/el.po
+++ b/src/bin/pg_verifybackup/po/el.po
@@ -494,8 +494,8 @@ msgstr "  -s, --skip-checksums        παράκαμψε την επαλήθευ
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/es.po b/src/bin/pg_verifybackup/po/es.po
index 0cb958f3448..7f729fa35ba 100644
--- a/src/bin/pg_verifybackup/po/es.po
+++ b/src/bin/pg_verifybackup/po/es.po
@@ -495,8 +495,8 @@ msgstr "  -s, --skip-checksums        omitir la verificación de la suma de comp
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    utilizar la ruta especificada para los archivos WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    utilizar la ruta especificada para los archivos WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/fr.po b/src/bin/pg_verifybackup/po/fr.po
index da8c72f6427..09937966fa7 100644
--- a/src/bin/pg_verifybackup/po/fr.po
+++ b/src/bin/pg_verifybackup/po/fr.po
@@ -498,8 +498,8 @@ msgstr "  -s, --skip-checksums        ignore la vérification des sommes de cont
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/it.po b/src/bin/pg_verifybackup/po/it.po
index 317b0b71e7f..4da68d0074e 100644
--- a/src/bin/pg_verifybackup/po/it.po
+++ b/src/bin/pg_verifybackup/po/it.po
@@ -472,8 +472,8 @@ msgstr "  -s, --skip-checksums         salta la verifica del checksum\n"
 
 #: pg_verifybackup.c:911
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH     usa il percorso specificato per i file WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH     usa il percorso specificato per i file WAL\n"
 
 #: pg_verifybackup.c:912
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ja.po b/src/bin/pg_verifybackup/po/ja.po
index c910fb236cc..a948959b54f 100644
--- a/src/bin/pg_verifybackup/po/ja.po
+++ b/src/bin/pg_verifybackup/po/ja.po
@@ -672,8 +672,8 @@ msgstr "  -s, --skip-checksums        チェックサム検証をスキップ\n"
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    WALファイルに指定したパスを使用する\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    WALファイルに指定したパスを使用する\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ka.po b/src/bin/pg_verifybackup/po/ka.po
index 982751984c7..ef2799316a8 100644
--- a/src/bin/pg_verifybackup/po/ka.po
+++ b/src/bin/pg_verifybackup/po/ka.po
@@ -784,8 +784,8 @@ msgstr "  -s, --skip-checksums        საკონტროლო ჯამ
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ko.po b/src/bin/pg_verifybackup/po/ko.po
index acdc3da5e02..eaf91ef1e98 100644
--- a/src/bin/pg_verifybackup/po/ko.po
+++ b/src/bin/pg_verifybackup/po/ko.po
@@ -501,8 +501,8 @@ msgstr "  -s, --skip-checksums        체크섬 검사 건너뜀\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=경로    WAL 파일이 있는 경로 지정\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=경로    WAL 파일이 있는 경로 지정\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ru.po b/src/bin/pg_verifybackup/po/ru.po
index 64005feedfd..7fb0e5ab1f6 100644
--- a/src/bin/pg_verifybackup/po/ru.po
+++ b/src/bin/pg_verifybackup/po/ru.po
@@ -507,9 +507,9 @@ msgstr "  -s, --skip-checksums        пропустить проверку ко
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
 msgstr ""
-"  -w, --wal-directory=ПУТЬ    использовать заданный путь к файлам WAL\n"
+"  -w, --wal-path=ПУТЬ    использовать заданный путь к файлам WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/sv.po b/src/bin/pg_verifybackup/po/sv.po
index 17240feeb5c..97125838e8c 100644
--- a/src/bin/pg_verifybackup/po/sv.po
+++ b/src/bin/pg_verifybackup/po/sv.po
@@ -492,8 +492,8 @@ msgstr "  -s, --skip-checksums        hoppa över verifiering av kontrollsummor\
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=SÖKVÄG  använd denna sökväg till WAL-filer\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=SÖKVÄG  använd denna sökväg till WAL-filer\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/uk.po b/src/bin/pg_verifybackup/po/uk.po
index 034b9764232..63f8041ab38 100644
--- a/src/bin/pg_verifybackup/po/uk.po
+++ b/src/bin/pg_verifybackup/po/uk.po
@@ -484,8 +484,8 @@ msgstr "  -s, --skip-checksums не перевіряти контрольні с
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH використовувати вказаний шлях для файлів WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH використовувати вказаний шлях для файлів WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_CN.po b/src/bin/pg_verifybackup/po/zh_CN.po
index b7d97c8976d..fb6fcae8b82 100644
--- a/src/bin/pg_verifybackup/po/zh_CN.po
+++ b/src/bin/pg_verifybackup/po/zh_CN.po
@@ -465,8 +465,8 @@ msgstr "  -s, --skip-checksums        跳过校验和验证\n"
 
 #: pg_verifybackup.c:919
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    对WAL文件使用指定路径\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    对WAL文件使用指定路径\n"
 
 #: pg_verifybackup.c:920
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_TW.po b/src/bin/pg_verifybackup/po/zh_TW.po
index c1b710b0a36..568f972b0bb 100644
--- a/src/bin/pg_verifybackup/po/zh_TW.po
+++ b/src/bin/pg_verifybackup/po/zh_TW.po
@@ -555,8 +555,8 @@ msgstr "  -s, --skip-checksums        跳過檢查碼驗證\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    用指定的路徑存放 WAL 檔\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    用指定的路徑存放 WAL 檔\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/t/007_wal.pl b/src/bin/pg_verifybackup/t/007_wal.pl
index babc4f0a86b..b07f80719b0 100644
--- a/src/bin/pg_verifybackup/t/007_wal.pl
+++ b/src/bin/pg_verifybackup/t/007_wal.pl
@@ -42,10 +42,10 @@ command_ok([ 'pg_verifybackup', '--no-parse-wal', $backup_path ],
 command_ok(
 	[
 		'pg_verifybackup',
-		'--wal-directory' => $relocated_pg_wal,
+		'--wal-path' => $relocated_pg_wal,
 		$backup_path
 	],
-	'--wal-directory can be used to specify WAL directory');
+	'--wal-path can be used to specify WAL directory');
 
 # Move directory back to original location.
 rename($relocated_pg_wal, $original_pg_wal) || die "rename pg_wal back: $!";
-- 
2.47.1

From 877dd072349fbfeb4a39f2f3cca13ba4b68d0912 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 17 Jul 2025 16:39:36 +0530
Subject: [PATCH v2 9/9] pg_verifybackup: enabled WAL parsing for tar-format
 backup

Now that pg_waldump supports decoding from tar archives, we should
leverage this functionality to remove the previous restriction on WAL
parsing for tar-backed formats.
---
 doc/src/sgml/ref/pg_verifybackup.sgml         |  5 +-
 src/bin/pg_verifybackup/pg_verifybackup.c     | 66 +++++++++++++------
 src/bin/pg_verifybackup/t/002_algorithm.pl    |  4 --
 src/bin/pg_verifybackup/t/003_corruption.pl   |  4 +-
 src/bin/pg_verifybackup/t/008_untar.pl        |  3 +-
 src/bin/pg_verifybackup/t/010_client_untar.pl |  3 +-
 6 files changed, 50 insertions(+), 35 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index e9b8bfd51b1..16b50b5a4df 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -36,10 +36,7 @@ PostgreSQL documentation
    <literal>backup_manifest</literal> generated by the server at the time
    of the backup. The backup may be stored either in the "plain" or the "tar"
    format; this includes tar-format backups compressed with any algorithm
-   supported by <application>pg_basebackup</application>. However, at present,
-   <literal>WAL</literal> verification is supported only for plain-format
-   backups. Therefore, if the backup is stored in tar-format, the
-   <literal>-n, --no-parse-wal</literal> option should be used.
+   supported by <application>pg_basebackup</application>.
   </para>
 
   <para>
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 1ee400199da..4bfe6fdff16 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -74,7 +74,9 @@ pg_noreturn static void report_manifest_error(JsonManifestParseContext *context,
 											  const char *fmt,...)
 			pg_attribute_printf(2, 3);
 
-static void verify_tar_backup(verifier_context *context, DIR *dir);
+static void verify_tar_backup(verifier_context *context, DIR *dir,
+							  char **base_archive_path,
+							  char **wal_archive_path);
 static void verify_plain_backup_directory(verifier_context *context,
 										  char *relpath, char *fullpath,
 										  DIR *dir);
@@ -83,7 +85,9 @@ static void verify_plain_backup_file(verifier_context *context, char *relpath,
 static void verify_control_file(const char *controlpath,
 								uint64 manifest_system_identifier);
 static void precheck_tar_backup_file(verifier_context *context, char *relpath,
-									 char *fullpath, SimplePtrList *tarfiles);
+									 char *fullpath, SimplePtrList *tarfiles,
+									 char **base_archive_path,
+									 char **wal_archive_path);
 static void verify_tar_file(verifier_context *context, char *relpath,
 							char *fullpath, astreamer *streamer);
 static void report_extra_backup_files(verifier_context *context);
@@ -136,6 +140,8 @@ main(int argc, char **argv)
 	bool		no_parse_wal = false;
 	bool		quiet = false;
 	char	   *wal_path = NULL;
+	char	   *base_archive_path = NULL;
+	char	   *wal_archive_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -327,17 +333,6 @@ main(int argc, char **argv)
 		pfree(path);
 	}
 
-	/*
-	 * XXX: In the future, we should consider enhancing pg_waldump to read WAL
-	 * files from an archive.
-	 */
-	if (!no_parse_wal && context.format == 't')
-	{
-		pg_log_error("pg_waldump cannot read tar files");
-		pg_log_error_hint("You must use -n/--no-parse-wal when verifying a tar-format backup.");
-		exit(1);
-	}
-
 	/*
 	 * Perform the appropriate type of verification appropriate based on the
 	 * backup format. This will close 'dir'.
@@ -346,7 +341,7 @@ main(int argc, char **argv)
 		verify_plain_backup_directory(&context, NULL, context.backup_directory,
 									  dir);
 	else
-		verify_tar_backup(&context, dir);
+		verify_tar_backup(&context, dir, &base_archive_path, &wal_archive_path);
 
 	/*
 	 * The "matched" flag should now be set on every entry in the hash table.
@@ -364,9 +359,28 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
-	/* By default, look for the WAL in the backup directory, too. */
+	/*
+	 * By default, WAL files are expected to be found in the backup directory
+	 * for plain-format backups. In the case of tar-format backups, if a
+	 * separate WAL archive is not found, the WAL files are most likely
+	 * included within the main data directory archive.
+	 */
 	if (wal_path == NULL)
-		wal_path = psprintf("%s/pg_wal", context.backup_directory);
+	{
+		if (context.format == 'p')
+			wal_path = psprintf("%s/pg_wal", context.backup_directory);
+		else if (wal_archive_path)
+			wal_path = wal_archive_path;
+		else if (base_archive_path)
+			wal_path = base_archive_path;
+		else
+		{
+			pg_log_error("wal archive not found");
+			pg_log_error_hint("Specify the correct path using the option -w/--wal-path."
+							  "Or you must use -n/--no-parse-wal when verifying a tar-format backup.");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
@@ -787,7 +801,8 @@ verify_control_file(const char *controlpath, uint64 manifest_system_identifier)
  * close when we're done with it.
  */
 static void
-verify_tar_backup(verifier_context *context, DIR *dir)
+verify_tar_backup(verifier_context *context, DIR *dir, char **base_archive_path,
+				  char **wal_archive_path)
 {
 	struct dirent *dirent;
 	SimplePtrList tarfiles = {NULL, NULL};
@@ -816,7 +831,8 @@ verify_tar_backup(verifier_context *context, DIR *dir)
 			char	   *fullpath;
 
 			fullpath = psprintf("%s/%s", context->backup_directory, filename);
-			precheck_tar_backup_file(context, filename, fullpath, &tarfiles);
+			precheck_tar_backup_file(context, filename, fullpath, &tarfiles,
+									 base_archive_path, wal_archive_path);
 			pfree(fullpath);
 		}
 	}
@@ -875,11 +891,13 @@ verify_tar_backup(verifier_context *context, DIR *dir)
  *
  * The arguments to this function are mostly the same as the
  * verify_plain_backup_file. The additional argument outputs a list of valid
- * tar files.
+ * tar files, along with the full paths to the main archive and the WAL
+ * directory archive.
  */
 static void
 precheck_tar_backup_file(verifier_context *context, char *relpath,
-						 char *fullpath, SimplePtrList *tarfiles)
+						 char *fullpath, SimplePtrList *tarfiles,
+						 char **base_archive_path, char **wal_archive_path)
 {
 	struct stat sb;
 	Oid			tblspc_oid = InvalidOid;
@@ -918,9 +936,17 @@ precheck_tar_backup_file(verifier_context *context, char *relpath,
 	 * extension such as .gz, .lz4, or .zst.
 	 */
 	if (strncmp("base", relpath, 4) == 0)
+	{
 		suffix = relpath + 4;
+
+		*base_archive_path = pstrdup(fullpath);
+	}
 	else if (strncmp("pg_wal", relpath, 6) == 0)
+	{
 		suffix = relpath + 6;
+
+		*wal_archive_path = pstrdup(fullpath);
+	}
 	else
 	{
 		/* Expected a <tablespaceoid>.tar file here. */
diff --git a/src/bin/pg_verifybackup/t/002_algorithm.pl b/src/bin/pg_verifybackup/t/002_algorithm.pl
index ae16c11bc4d..4f284a9e828 100644
--- a/src/bin/pg_verifybackup/t/002_algorithm.pl
+++ b/src/bin/pg_verifybackup/t/002_algorithm.pl
@@ -30,10 +30,6 @@ sub test_checksums
 	{
 		# Add switch to get a tar-format backup
 		push @backup, ('--format' => 'tar');
-
-		# Add switch to skip WAL verification, which is not yet supported for
-		# tar-format backups
-		push @verify, ('--no-parse-wal');
 	}
 
 	# A backup with a bogus algorithm should fail.
diff --git a/src/bin/pg_verifybackup/t/003_corruption.pl b/src/bin/pg_verifybackup/t/003_corruption.pl
index 1dd60f709cf..f1ebdbb46b4 100644
--- a/src/bin/pg_verifybackup/t/003_corruption.pl
+++ b/src/bin/pg_verifybackup/t/003_corruption.pl
@@ -193,10 +193,8 @@ for my $scenario (@scenario)
 			command_ok([ $tar, '-cf' => "$tar_backup_path/base.tar", '.' ]);
 			chdir($cwd) || die "chdir: $!";
 
-			# Now check that the backup no longer verifies. We must use -n
-			# here, because pg_waldump can't yet read WAL from a tarfile.
 			command_fails_like(
-				[ 'pg_verifybackup', '--no-parse-wal', $tar_backup_path ],
+				[ 'pg_verifybackup', $tar_backup_path ],
 				$scenario->{'fails_like'},
 				"corrupt backup fails verification: $name");
 
diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index bc3d6b352ad..0cfe1f9532c 100644
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -123,8 +123,7 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index b62faeb5acf..76269a73673 100644
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -137,8 +137,7 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
-- 
2.47.1

From 233cf0977b18100916b0204ad7e57445c420dae6 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 24 Jun 2025 11:33:20 +0530
Subject: [PATCH v2 1/9] Refactor: pg_waldump: Move some declarations to new
 pg_waldump.h

This is in preparation for adding a second source file to this
directory.
---
 src/bin/pg_waldump/pg_waldump.c | 11 ++---------
 src/bin/pg_waldump/pg_waldump.h | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 9 deletions(-)
 create mode 100644 src/bin/pg_waldump/pg_waldump.h

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 13d3ec2f5be..a49b2fd96c7 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -29,6 +29,7 @@
 #include "common/logging.h"
 #include "common/relpath.h"
 #include "getopt_long.h"
+#include "pg_waldump.h"
 #include "rmgrdesc.h"
 #include "storage/bufpage.h"
 
@@ -39,19 +40,11 @@
 
 static const char *progname;
 
-static int	WalSegSz;
+int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 static volatile sig_atomic_t time_to_stop = false;
 
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
-typedef struct XLogDumpPrivate
-{
-	TimeLineID	timeline;
-	XLogRecPtr	startptr;
-	XLogRecPtr	endptr;
-	bool		endptr_reached;
-} XLogDumpPrivate;
-
 typedef struct XLogDumpConfig
 {
 	/* display options */
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
new file mode 100644
index 00000000000..9e62b64ead5
--- /dev/null
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -0,0 +1,27 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_waldump.h - decode and display WAL
+ *
+ * Copyright (c) 2013-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  src/bin/pg_waldump/pg_waldump.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_WALDUMP_H
+#define PG_WALDUMP_H
+
+#include "access/xlogdefs.h"
+
+extern int	WalSegSz;
+
+/* Contains the necessary information to drive WAL decoding */
+typedef struct XLogDumpPrivate
+{
+	TimeLineID	timeline;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
+	bool		endptr_reached;
+} XLogDumpPrivate;
+
+#endif		/* end of PG_WALDUMP_H */
-- 
2.47.1

From b46d48d7cc9fc42257f3d6da6850ff20f9461ae9 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 26 Jun 2025 11:42:53 +0530
Subject: [PATCH v2 2/9] Refactor: pg_waldump: Separate logic used to calculate
 the required read size.

This refactoring prepares the codebase for an upcoming patch that will
support reading WAL from tar files. The logic for calculating the
required read size has been updated to handle both normal WAL files
and WAL files located inside a tar archive.
---
 src/bin/pg_waldump/pg_waldump.c | 39 ++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index a49b2fd96c7..8d0cd9e7156 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -326,6 +326,29 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/* Returns the size in bytes of the data to be read. */
+static inline int
+required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
+				  int reqLen)
+{
+	int			count = XLOG_BLCKSZ;
+
+	if (private->endptr != InvalidXLogRecPtr)
+	{
+		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
+			count = XLOG_BLCKSZ;
+		else if (targetPagePtr + reqLen <= private->endptr)
+			count = private->endptr - targetPagePtr;
+		else
+		{
+			private->endptr_reached = true;
+			return -1;
+		}
+	}
+
+	return count;
+}
+
 /* pg_waldump's XLogReaderRoutine->segment_open callback */
 static void
 WALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
@@ -383,21 +406,11 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = XLOG_BLCKSZ;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
-	if (private->endptr != InvalidXLogRecPtr)
-	{
-		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
-			count = XLOG_BLCKSZ;
-		else if (targetPagePtr + reqLen <= private->endptr)
-			count = private->endptr - targetPagePtr;
-		else
-		{
-			private->endptr_reached = true;
-			return -1;
-		}
-	}
+	if (private->endptr_reached)
+		return -1;
 
 	if (!WALRead(state, readBuff, targetPagePtr, count, private->timeline,
 				 &errinfo))
-- 
2.47.1

From 8e3236330522fae0674508cebc7d2f1d8379271f Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 30 Jul 2025 12:43:30 +0530
Subject: [PATCH v2 3/9] Refactor: pg_waldump: Restructure TAP tests.

Restructured some tests to run inside a loop, facilitating their
re-execution for decoding WAL from tar archives.
---
 src/bin/pg_waldump/t/001_basic.pl | 123 ++++++++++++++++--------------
 1 file changed, 67 insertions(+), 56 deletions(-)

diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index f26d75e01cf..1b712e8d74d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -198,28 +198,6 @@ command_like(
 	],
 	qr/./,
 	'runs with start and end segment specified');
-command_fails_like(
-	[ 'pg_waldump', '--path' => $node->data_dir ],
-	qr/error: no start WAL location given/,
-	'path option requires start location');
-command_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-		'--end' => $end_lsn,
-	],
-	qr/./,
-	'runs with path option and start and end locations');
-command_fails_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-	],
-	qr/error: error in WAL record at/,
-	'falling off the end of the WAL results in an error');
-
 command_like(
 	[
 		'pg_waldump', '--quiet',
@@ -227,15 +205,6 @@ command_like(
 	],
 	qr/^$/,
 	'no output with --quiet option');
-command_fails_like(
-	[
-		'pg_waldump', '--quiet',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn
-	],
-	qr/error: error in WAL record at/,
-	'errors are shown with --quiet');
-
 
 # Test for: Display a message that we're skipping data if `from`
 # wasn't a pointer to the start of a record.
@@ -272,7 +241,6 @@ sub test_pg_waldump
 
 	my $result = IPC::Run::run [
 		'pg_waldump',
-		'--path' => $node->data_dir,
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
 		@opts
@@ -288,38 +256,81 @@ sub test_pg_waldump
 
 my @lines;
 
-@lines = test_pg_waldump;
-is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
+my @scenario = (
+	{
+		'path' => $node->data_dir
+	});
 
-@lines = test_pg_waldump('--limit' => 6);
-is(@lines, 6, 'limit option observed');
+for my $scenario (@scenario)
+{
+	my $path = $scenario->{'path'};
 
-@lines = test_pg_waldump('--fullpage');
-is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
+	SKIP:
+	{
+		command_fails_like(
+			[ 'pg_waldump', '--path' => $path ],
+			qr/error: no start WAL location given/,
+			'path option requires start location');
+		command_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+				'--end' => $end_lsn,
+			],
+			qr/./,
+			'runs with path option and start and end locations');
+		command_fails_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+			],
+			qr/error: error in WAL record at/,
+			'falling off the end of the WAL results in an error');
 
-@lines = test_pg_waldump('--stats');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		command_fails_like(
+			[
+				'pg_waldump', '--quiet',
+				'--path' => $path,
+				'--start' => $start_lsn
+			],
+			qr/error: error in WAL record at/,
+			'errors are shown with --quiet');
 
-@lines = test_pg_waldump('--stats=record');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		@lines = test_pg_waldump('--path' => $path);
+		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-@lines = test_pg_waldump('--rmgr' => 'Btree');
-is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		is(@lines, 6, 'limit option observed');
 
-@lines = test_pg_waldump('--fork' => 'init');
-is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
-is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
-	0, 'only lines for selected relation');
+		@lines = test_pg_waldump('--path' => $path, '--stats');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
-	'--block' => 1);
-is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
+		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+
+		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
+		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
+			0, 'only lines for selected relation');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
+			'--block' => 1);
+		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+	}
+}
 
 done_testing();
-- 
2.47.1

From 4baa0189d624cd4606dcab5f5417cf7d305a8223 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 29 Jul 2025 14:59:01 +0530
Subject: [PATCH v2 4/9] pg_waldump: Rename directory creation routine for
 generalized use.

The create_fullpage_directory() function, currently used only for
storing full-page images from WAL records, should be renamed to a more
generalized name. This would allow it to be reused in future patches
for creating other directories as needed.
---
 src/bin/pg_waldump/pg_waldump.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 8d0cd9e7156..4775275c07a 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -114,11 +114,11 @@ verify_directory(const char *directory)
 }
 
 /*
- * Create if necessary the directory storing the full-page images extracted
- * from the WAL records read.
+ * Create the directory if it doesn't exist. Report an error if creation fails
+ * or if an existing directory is not empty.
  */
 static void
-create_fullpage_directory(char *path)
+create_directory(char *path)
 {
 	int			ret;
 
@@ -1112,8 +1112,12 @@ main(int argc, char **argv)
 		}
 	}
 
+	/*
+	 * Create if necessary the directory storing the full-page images
+	 * extracted from the WAL records read.
+	 */
 	if (config.save_fullpage_path != NULL)
-		create_fullpage_directory(config.save_fullpage_path);
+		create_directory(config.save_fullpage_path);
 
 	/* parse files as start/end boundaries, extract path if not specified */
 	if (optind < argc)
-- 
2.47.1

From 5f97922e34e7d5a523dbe718a1b61ebb08c7403e Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 18:37:59 +0530
Subject: [PATCH v2 5/9] pg_waldump: Add support for archived WAL decoding.

pg_waldump can now accept the path to a tar archive containing WAL
files and decode them. This feature was added primarily for
pg_verifybackup, which previously disabled WAL parsing for
tar-formatted backups.

Note that this patch requires that the WAL files within the archive be
in sequential order; an error will be reported otherwise. The next
patch is planned to remove this restriction.
---
 doc/src/sgml/ref/pg_waldump.sgml       |   8 +-
 src/bin/pg_waldump/Makefile            |   7 +-
 src/bin/pg_waldump/astreamer_waldump.c | 378 +++++++++++++++++++++++++
 src/bin/pg_waldump/meson.build         |   4 +-
 src/bin/pg_waldump/pg_waldump.c        | 361 +++++++++++++++++++----
 src/bin/pg_waldump/pg_waldump.h        |  21 +-
 src/bin/pg_waldump/t/001_basic.pl      |  84 +++++-
 src/tools/pgindent/typedefs.list       |   1 +
 8 files changed, 785 insertions(+), 79 deletions(-)
 create mode 100644 src/bin/pg_waldump/astreamer_waldump.c

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index ce23add5577..d004bb0f67e 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -141,13 +141,17 @@ PostgreSQL documentation
       <term><option>--path=<replaceable>path</replaceable></option></term>
       <listitem>
        <para>
-        Specifies a directory to search for WAL segment files or a
-        directory with a <literal>pg_wal</literal> subdirectory that
+        Specifies a tar archive or a directory to search for WAL segment files
+        or a directory with a <literal>pg_wal</literal> subdirectory that
         contains such files.  The default is to search in the current
         directory, the <literal>pg_wal</literal> subdirectory of the
         current directory, and the <literal>pg_wal</literal> subdirectory
         of <envar>PGDATA</envar>.
        </para>
+       <para>
+        If a tar archive is provided, its WAL segment files must be in
+        sequential order; otherwise, an error will be reported.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index 4c1ee649501..b234613eb50 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -3,6 +3,9 @@
 PGFILEDESC = "pg_waldump - decode and display WAL"
 PGAPPICON=win32
 
+# make these available to TAP test scripts
+export TAR
+
 subdir = src/bin/pg_waldump
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
@@ -12,11 +15,13 @@ OBJS = \
 	$(WIN32RES) \
 	compat.o \
 	pg_waldump.o \
+	astreamer_waldump.o \
 	rmgrdesc.o \
 	xlogreader.o \
 	xlogstats.o
 
-override CPPFLAGS := -DFRONTEND $(CPPFLAGS)
+override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
diff --git a/src/bin/pg_waldump/astreamer_waldump.c b/src/bin/pg_waldump/astreamer_waldump.c
new file mode 100644
index 00000000000..916d388ef0c
--- /dev/null
+++ b/src/bin/pg_waldump/astreamer_waldump.c
@@ -0,0 +1,378 @@
+/*-------------------------------------------------------------------------
+ *
+ * astreamer_waldump.c
+ *		A generic facility for reading WAL data from tar archives via archive
+ *		streamer.
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/bin/pg_waldump/astreamer_waldump.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <unistd.h>
+
+#include "access/xlog_internal.h"
+#include "access/xlogdefs.h"
+#include "common/logging.h"
+#include "fe_utils/simple_list.h"
+#include "pg_waldump.h"
+
+/*
+ * How many bytes should we try to read from a file at once?
+ */
+#define READ_CHUNK_SIZE				(128 * 1024)
+
+typedef struct astreamer_waldump
+{
+	/* These fields don't change once initialized. */
+	astreamer	base;
+	XLogSegNo	startSegNo;
+	XLogSegNo	endSegNo;
+	XLogDumpPrivate *privateInfo;
+
+	/* These fields change with archive member. */
+	bool		skipThisSeg;
+	XLogSegNo	nextSegNo;		/* Next expected segment to stream */
+} astreamer_waldump;
+
+static int	astreamer_archive_read(XLogDumpPrivate *privateInfo);
+static void astreamer_waldump_content(astreamer *streamer,
+									  astreamer_member *member,
+									  const char *data, int len,
+									  astreamer_archive_context context);
+static void astreamer_waldump_finalize(astreamer *streamer);
+static void astreamer_waldump_free(astreamer *streamer);
+
+static bool member_is_relevant_wal(astreamer_member *member,
+								   TimeLineID startTimeLineID,
+								   XLogSegNo startSegNo,
+								   XLogSegNo endSegNo,
+								   XLogSegNo nextSegNo,
+								   XLogSegNo *curSegNo,
+								   TimeLineID *curSegTimeline);
+
+static const astreamer_ops astreamer_waldump_ops = {
+	.content = astreamer_waldump_content,
+	.finalize = astreamer_waldump_finalize,
+	.free = astreamer_waldump_free
+};
+
+/*
+ * Copies WAL data from astreamer to readBuff; if unavailable, fetches more
+ * from the tar archive via astreamer.
+ */
+int
+astreamer_wal_read(char *readBuff, XLogRecPtr targetPagePtr, Size count,
+				   XLogDumpPrivate *privateInfo)
+{
+	char	   *p = readBuff;
+	Size		nbytes = count;
+	XLogRecPtr	recptr = targetPagePtr;
+	volatile StringInfo astreamer_buf = privateInfo->archive_streamer_buf;
+
+	while (nbytes > 0)
+	{
+		char	   *buf = astreamer_buf->data;
+		int			len = astreamer_buf->len;
+
+		/* WAL record range that the buffer contains */
+		XLogRecPtr	endPtr = privateInfo->archive_streamer_read_ptr;
+		XLogRecPtr	startPtr = (endPtr > len) ? endPtr - len : 0;
+
+		/*
+		 * Ignore existing data if the required target page has not yet been
+		 * read.
+		 */
+		if (recptr >= endPtr)
+		{
+			len = 0;
+
+			/* Reset the buffer */
+			resetStringInfo(astreamer_buf);
+		}
+
+		if (len > 0 && recptr > startPtr)
+		{
+			int			skipBytes = 0;
+
+			/*
+			 * The required offset is not at the start of the archive streamer
+			 * buffer, so skip bytes until reaching the desired offset of the
+			 * target page.
+			 */
+			skipBytes = recptr - startPtr;
+
+			buf += skipBytes;
+			len -= skipBytes;
+		}
+
+		if (len > 0)
+		{
+			int			readBytes = len >= nbytes ? nbytes : len;
+
+			/*
+			 * Ensure we are reading the correct page, unless we've received
+			 * an invalid record pointer. In that specific case, it's
+			 * acceptable to read any page.
+			 */
+			Assert(XLogRecPtrIsInvalid(recptr) ||
+				   (recptr >= startPtr && recptr < endPtr));
+
+			memcpy(p, buf, readBytes);
+
+			/* Update state for read */
+			nbytes -= readBytes;
+			p += readBytes;
+			recptr += readBytes;
+		}
+		else
+		{
+			/* Fetch more data */
+			if (astreamer_archive_read(privateInfo) == 0)
+				break;			/* No data remaining */
+		}
+	}
+
+	return (count - nbytes) ? (count - nbytes) : -1;
+}
+
+/*
+ * Reads the archive and passes it to the archive streamer for decompression.
+ */
+static int
+astreamer_archive_read(XLogDumpPrivate *privateInfo)
+{
+	int			rc;
+	char	   *buffer;
+
+	buffer = pg_malloc(READ_CHUNK_SIZE * sizeof(uint8));
+
+	/* Read more data from the tar file */
+	rc = read(privateInfo->archive_fd, buffer, READ_CHUNK_SIZE);
+	if (rc < 0)
+		pg_fatal("could not read file \"%s\": %m",
+				 privateInfo->archive_name);
+
+	/*
+	 * Decrypt (if required), and then parse the previously read contents of
+	 * the tar file.
+	 */
+	if (rc > 0)
+		astreamer_content(privateInfo->archive_streamer, NULL,
+						  buffer, rc, ASTREAMER_UNKNOWN);
+	pg_free(buffer);
+
+	return rc;
+}
+
+/*
+ * Create an astreamer that can read WAL from tar file.
+ */
+astreamer *
+astreamer_waldump_content_new(astreamer *next, XLogRecPtr startptr,
+							  XLogRecPtr endPtr, XLogDumpPrivate *privateInfo)
+{
+	astreamer_waldump *streamer;
+
+	streamer = palloc0(sizeof(astreamer_waldump));
+	*((const astreamer_ops **) &streamer->base.bbs_ops) =
+		&astreamer_waldump_ops;
+
+	streamer->base.bbs_next = next;
+	initStringInfo(&streamer->base.bbs_buffer);
+
+	if (XLogRecPtrIsInvalid(startptr))
+		streamer->startSegNo = 0;
+	else
+	{
+		XLByteToSeg(startptr, streamer->startSegNo, WalSegSz);
+
+		/*
+		 * Initialize the record pointer to the beginning of the first
+		 * segment; this pointer will track the WAL record reading status.
+		 */
+		XLogSegNoOffsetToRecPtr(streamer->startSegNo, 0, WalSegSz,
+								privateInfo->archive_streamer_read_ptr);
+	}
+
+	if (XLogRecPtrIsInvalid(endPtr))
+		streamer->endSegNo = UINT64_MAX;
+	else
+		XLByteToSeg(endPtr, streamer->endSegNo, WalSegSz);
+
+	streamer->nextSegNo = streamer->startSegNo;
+	streamer->privateInfo = privateInfo;
+
+	return &streamer->base;
+}
+
+/*
+ * Main entry point of the archive streamer for reading WAL from a tar file.
+ */
+static void
+astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
+						  const char *data, int len,
+						  astreamer_archive_context context)
+{
+	astreamer_waldump *mystreamer = (astreamer_waldump *) streamer;
+	XLogDumpPrivate *privateInfo = mystreamer->privateInfo;
+
+	Assert(context != ASTREAMER_UNKNOWN);
+
+	switch (context)
+	{
+		case ASTREAMER_MEMBER_HEADER:
+			{
+				XLogSegNo	segNo;
+				TimeLineID	timeline;
+
+				pg_log_debug("pg_waldump: reading \"%s\"", member->pathname);
+
+				mystreamer->skipThisSeg = false;
+
+				if (!member_is_relevant_wal(member,
+											privateInfo->timeline,
+											mystreamer->startSegNo,
+											mystreamer->endSegNo,
+											mystreamer->nextSegNo,
+											&segNo, &timeline))
+				{
+					mystreamer->skipThisSeg = true;
+					break;
+				}
+
+				/*
+				 * If nextSegNo is 0, the check is skipped, and any WAL file
+				 * can be read -- this typically occurs during initial
+				 * verification.
+				 */
+				if (mystreamer->nextSegNo == 0)
+					break;
+
+				/* WAL segments must be archived in order */
+				if (mystreamer->nextSegNo != segNo)
+				{
+					pg_log_error("WAL files are not archived in sequential order");
+					pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
+										mystreamer->nextSegNo, segNo);
+					exit(1);
+				}
+
+				/*
+				 * We track the reading of WAL segment records using a pointer
+				 * that's continuously incremented by the length of the
+				 * received data. This pointer is crucial for serving WAL page
+				 * requests from the WAL decoding routine, so it must be
+				 * accurate.
+				 */
+#ifdef USE_ASSERT_CHECKING
+				if (mystreamer->nextSegNo != 0)
+				{
+					XLogRecPtr	recPtr;
+
+					XLogSegNoOffsetToRecPtr(segNo, 0, WalSegSz, recPtr);
+					Assert(privateInfo->archive_streamer_read_ptr == recPtr);
+				}
+#endif
+
+				/* Save the timeline */
+				privateInfo->timeline = timeline;
+
+				/* Update the next expected segment number */
+				mystreamer->nextSegNo += 1;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_CONTENTS:
+			/* Skip this segment */
+			if (mystreamer->skipThisSeg)
+				break;
+
+			/* Or, copy contents to buffer */
+			privateInfo->archive_streamer_read_ptr += len;
+			astreamer_buffer_bytes(streamer, &data, &len, len);
+			break;
+
+		case ASTREAMER_MEMBER_TRAILER:
+			break;
+
+		case ASTREAMER_ARCHIVE_TRAILER:
+			break;
+
+		default:
+			/* Shouldn't happen. */
+			pg_fatal("unexpected state while parsing tar file");
+	}
+}
+
+/*
+ * End-of-stream processing for a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_finalize(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+}
+
+/*
+ * Free memory associated with a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_free(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+
+	pfree(streamer->bbs_buffer.data);
+	pfree(streamer);
+}
+
+/*
+ * Returns true if the archive member name matches the WAL naming format and
+ * the corresponding WAL segment falls within the WAL decoding target range;
+ * otherwise, returns false.
+ */
+static bool
+member_is_relevant_wal(astreamer_member *member, TimeLineID startTimeLineID,
+					   XLogSegNo startSegNo, XLogSegNo endSegNo,
+					   XLogSegNo nextSegNo, XLogSegNo *curSegNo,
+					   TimeLineID *curSegTimeline)
+{
+	int			pathlen;
+	XLogSegNo	segNo;
+	TimeLineID	timeline;
+	char	   *fname;
+
+	/* We are only interested in normal files. */
+	if (member->is_directory || member->is_link)
+		return false;
+
+	pathlen = strlen(member->pathname);
+	if (pathlen < XLOG_FNAME_LEN)
+		return false;
+
+	/* WAL file could be with full path */
+	fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+	if (!IsXLogFileName(fname))
+		return false;
+
+	/* Parse position from file */
+	XLogFromFileName(fname, &timeline, &segNo, WalSegSz);
+
+	/* Ignore the older timeline */
+	if (startTimeLineID > timeline)
+		return false;
+
+	/* Skip if the current segment is not the desired one */
+	if (startSegNo > segNo || endSegNo < segNo)
+		return false;
+
+	*curSegNo = segNo;
+	*curSegTimeline = timeline;
+
+	return true;
+}
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 937e0d68841..2a0300dc339 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -3,6 +3,7 @@
 pg_waldump_sources = files(
   'compat.c',
   'pg_waldump.c',
+  'astreamer_waldump.c',
   'rmgrdesc.c',
 )
 
@@ -18,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, lz4, zstd],
+  dependencies: [frontend_code, lz4, zstd, libpq],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
@@ -29,6 +30,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'TAR': tar.found() ? tar.full_path() : ''},
     'tests': [
       't/001_basic.pl',
       't/002_save_fullpage.pl',
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 4775275c07a..64f3a65b735 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -182,10 +182,9 @@ open_file_in_directory(const char *directory, const char *fname)
 {
 	int			fd = -1;
 	char		fpath[MAXPGPATH];
+	char	   *dir = directory ? (char *) directory : ".";
 
-	Assert(directory != NULL);
-
-	snprintf(fpath, MAXPGPATH, "%s/%s", directory, fname);
+	snprintf(fpath, MAXPGPATH, "%s/%s", dir, fname);
 	fd = open(fpath, O_RDONLY | PG_BINARY, 0);
 
 	if (fd < 0 && errno != ENOENT)
@@ -326,6 +325,160 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/*
+ * Returns true if the given file is a tar archive and outputs its compression
+ * algorithm.
+ */
+static bool
+is_tar_file(const char *fname, pg_compress_algorithm *compression)
+{
+	int			fname_len = strlen(fname);
+	pg_compress_algorithm compress_algo;
+
+	/* Now, check the compression type of the tar */
+	if (fname_len > 4 &&
+		strcmp(fname + fname_len - 4, ".tar") == 0)
+		compress_algo = PG_COMPRESSION_NONE;
+	else if (fname_len > 4 &&
+			 strcmp(fname + fname_len - 4, ".tgz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 7 &&
+			 strcmp(fname + fname_len - 7, ".tar.gz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.lz4") == 0)
+		compress_algo = PG_COMPRESSION_LZ4;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.zst") == 0)
+		compress_algo = PG_COMPRESSION_ZSTD;
+	else
+		return false;
+
+	*compression = compress_algo;
+
+	return true;
+}
+
+/*
+ * Creates an appropriate chain of archive streamers for reading the given
+ * tar archive.
+ */
+static void
+setup_astreamer(XLogDumpPrivate *private, pg_compress_algorithm compression,
+				XLogRecPtr startptr, XLogRecPtr endptr)
+{
+	astreamer  *streamer = NULL;
+
+	streamer = astreamer_waldump_content_new(NULL, startptr, endptr, private);
+
+	/*
+	 * Final extracted WAL data will reside in this streamer. However, since
+	 * it sits at the bottom of the stack and isn't designed to propagate data
+	 * upward, we need to hold a pointer to its data buffer in order to copy.
+	 */
+	private->archive_streamer_buf = &streamer->bbs_buffer;
+
+	/* Before that we must parse the tar archive. */
+	streamer = astreamer_tar_parser_new(streamer);
+
+	/* Before that we must decompress, if archive is compressed. */
+	if (compression == PG_COMPRESSION_GZIP)
+		streamer = astreamer_gzip_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_LZ4)
+		streamer = astreamer_lz4_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_ZSTD)
+		streamer = astreamer_zstd_decompressor_new(streamer);
+
+	private->archive_streamer = streamer;
+}
+
+/*
+ * Initializes the archive reader for a tar file.
+ */
+static void
+init_tar_archive_reader(XLogDumpPrivate *private, char *waldir,
+						pg_compress_algorithm compression)
+{
+	int			fd;
+
+	/* Now, the tar archive and store its file descriptor */
+	fd = open_file_in_directory(waldir, private->archive_name);
+
+	if (fd < 0)
+		pg_fatal("could not open file \"%s\"", private->archive_name);
+
+	private->archive_fd = fd;
+
+	/* Setup tar archive reading facility */
+	setup_astreamer(private, compression, private->startptr, private->endptr);
+}
+
+/*
+ * Release the archive streamer chain and close the archive file.
+ */
+static void
+free_tar_archive_reader(XLogDumpPrivate *private)
+{
+	/*
+	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
+	 * flush any remaining buffered data or to ensure the end of the tar
+	 * archive is reached. However, when decoding a WAL file, once we hit the
+	 * end LSN, any remaining WAL data in the buffer or the tar archive's
+	 * unreached end can be safely ignored.
+	 */
+	astreamer_free(private->archive_streamer);
+
+	/* Close the file. */
+	if (close(private->archive_fd) != 0)
+		pg_log_error("could not close file \"%s\": %m",
+					 private->archive_name);
+}
+
+/*
+ * Reads a WAL page from the archive and verifies WAL segment size.
+ */
+static void
+verify_tar_archive(XLogDumpPrivate *private, const char *waldir,
+				   pg_compress_algorithm compression)
+{
+	PGAlignedXLogBlock buf;
+	int			r;
+
+	setup_astreamer(private, compression, InvalidXLogRecPtr, InvalidXLogRecPtr);
+
+	/* Now, the tar archive and store its file descriptor */
+	private->archive_fd = open_file_in_directory(waldir, private->archive_name);
+
+	if (private->archive_fd < 0)
+		pg_fatal("could not open file \"%s\"", private->archive_name);
+
+	/* Read a wal page */
+	r = astreamer_wal_read(buf.data, InvalidXLogRecPtr, XLOG_BLCKSZ, private);
+
+	/* Set WalSegSz if WAL data is successfully read */
+	if (r == XLOG_BLCKSZ)
+	{
+		XLogLongPageHeader longhdr = (XLogLongPageHeader) buf.data;
+
+		WalSegSz = longhdr->xlp_seg_size;
+
+		if (!IsValidWalSegSize(WalSegSz))
+		{
+			pg_log_error(ngettext("invalid WAL segment size in WAL file \"%s\" (%d byte)",
+								  "invalid WAL segment size in WAL file \"%s\" (%d bytes)",
+								  WalSegSz),
+						 private->archive_name, WalSegSz);
+			pg_log_error_detail("The WAL segment size must be a power of two between 1 MB and 1 GB.");
+			exit(1);
+		}
+	}
+	else
+		pg_fatal("could not read WAL data from \"%s\" archive: read %d of %d",
+				 private->archive_name, r, XLOG_BLCKSZ);
+
+	free_tar_archive_reader(private);
+}
+
 /* Returns the size in bytes of the data to be read. */
 static inline int
 required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
@@ -406,7 +559,7 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = required_read_len(private, targetPagePtr, reqLen);
+	int			count = required_read_len(private, targetPtr, reqLen);
 	WALReadError errinfo;
 
 	if (private->endptr_reached)
@@ -436,6 +589,44 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 	return count;
 }
 
+/*
+ * pg_waldump's XLogReaderRoutine->segment_open callback to support dumping WAL
+ * files from tar archives.
+ */
+static void
+TarWALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
+					  TimeLineID *tli_p)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->segment_close callback.
+ */
+static void
+TarWALDumpCloseSegment(XLogReaderState *state)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->page_read callback to support dumping WAL
+ * files from tar archives.
+ */
+static int
+TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				   XLogRecPtr targetPtr, char *readBuff)
+{
+	XLogDumpPrivate *private = state->private_data;
+	int			count = required_read_len(private, targetPtr, reqLen);
+
+	if (private->endptr_reached)
+		return -1;
+
+	/* Read the WAL page from the archive streamer */
+	return astreamer_wal_read(readBuff, targetPagePtr, count, private);
+}
+
 /*
  * Boolean to return whether the given WAL record matches a specific relation
  * and optionally block.
@@ -773,8 +964,8 @@ usage(void)
 	printf(_("  -F, --fork=FORK        only show records that modify blocks in fork FORK;\n"
 			 "                         valid names are main, fsm, vm, init\n"));
 	printf(_("  -n, --limit=N          number of records to display\n"));
-	printf(_("  -p, --path=PATH        directory in which to find WAL segment files or a\n"
-			 "                         directory with a ./pg_wal that contains such files\n"
+	printf(_("  -p, --path=PATH        tar archive or a directory in which to find WAL segment files or\n"
+			 "                         a directory with a ./pg_wal that contains such files\n"
 			 "                         (default: current directory, ./pg_wal, $PGDATA/pg_wal)\n"));
 	printf(_("  -q, --quiet            do not print any output, except for errors\n"));
 	printf(_("  -r, --rmgr=RMGR        only show records generated by resource manager RMGR;\n"
@@ -806,7 +997,11 @@ main(int argc, char **argv)
 	XLogRecord *record;
 	XLogRecPtr	first_record;
 	char	   *waldir = NULL;
+	char	   *walpath = NULL;
 	char	   *errormsg;
+	bool		is_tar = false;
+	XLogReaderRoutine *routine = NULL;
+	pg_compress_algorithm compression;
 
 	static struct option long_options[] = {
 		{"bkp-details", no_argument, NULL, 'b'},
@@ -938,7 +1133,7 @@ main(int argc, char **argv)
 				}
 				break;
 			case 'p':
-				waldir = pg_strdup(optarg);
+				walpath = pg_strdup(optarg);
 				break;
 			case 'q':
 				config.quiet = true;
@@ -1102,10 +1297,20 @@ main(int argc, char **argv)
 		goto bad_argument;
 	}
 
-	if (waldir != NULL)
+	if (walpath != NULL)
 	{
+		/* validate path points to tar archive */
+		if (is_tar_file(walpath, &compression))
+		{
+			char	   *fname = NULL;
+
+			split_path(walpath, &waldir, &fname);
+
+			private.archive_name = fname;
+			is_tar = true;
+		}
 		/* validate path points to directory */
-		if (!verify_directory(waldir))
+		else if (!verify_directory(walpath))
 		{
 			pg_log_error("could not open directory \"%s\": %m", waldir);
 			goto bad_argument;
@@ -1129,44 +1334,23 @@ main(int argc, char **argv)
 
 		split_path(argv[optind], &directory, &fname);
 
-		if (waldir == NULL && directory != NULL)
+		if (walpath == NULL && directory != NULL)
 		{
-			waldir = directory;
+			walpath = directory;
 
-			if (!verify_directory(waldir))
+			if (!verify_directory(walpath))
 				pg_fatal("could not open directory \"%s\": %m", waldir);
 		}
 
-		waldir = identify_target_directory(waldir, fname);
-		fd = open_file_in_directory(waldir, fname);
-		if (fd < 0)
-			pg_fatal("could not open file \"%s\"", fname);
-		close(fd);
-
-		/* parse position from file */
-		XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
-
-		if (XLogRecPtrIsInvalid(private.startptr))
-			XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
-		else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+		if (fname != NULL && is_tar_file(fname, &compression))
 		{
-			pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.startptr),
-						 fname);
-			goto bad_argument;
+			private.archive_name = fname;
+			waldir = walpath;
+			is_tar = true;
 		}
-
-		/* no second file specified, set end position */
-		if (!(optind + 1 < argc) && XLogRecPtrIsInvalid(private.endptr))
-			XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
-
-		/* parse ENDSEG if passed */
-		if (optind + 1 < argc)
+		else
 		{
-			XLogSegNo	endsegno;
-
-			/* ignore directory, already have that */
-			split_path(argv[optind + 1], &directory, &fname);
+			waldir = identify_target_directory(walpath, fname);
 
 			fd = open_file_in_directory(waldir, fname);
 			if (fd < 0)
@@ -1174,32 +1358,67 @@ main(int argc, char **argv)
 			close(fd);
 
 			/* parse position from file */
-			XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+			XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
 
-			if (endsegno < segno)
-				pg_fatal("ENDSEG %s is before STARTSEG %s",
-						 argv[optind + 1], argv[optind]);
+			if (XLogRecPtrIsInvalid(private.startptr))
+				XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
+			else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+			{
+				pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.startptr),
+							 fname);
+				goto bad_argument;
+			}
 
-			if (XLogRecPtrIsInvalid(private.endptr))
-				XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
-										private.endptr);
+			/* no second file specified, set end position */
+			if (!(optind + 1 < argc) && XLogRecPtrIsInvalid(private.endptr))
+				XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
 
-			/* set segno to endsegno for check of --end */
-			segno = endsegno;
-		}
+			/* parse ENDSEG if passed */
+			if (optind + 1 < argc)
+			{
+				XLogSegNo	endsegno;
 
+				/* ignore directory, already have that */
+				split_path(argv[optind + 1], &directory, &fname);
 
-		if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
-			private.endptr != (segno + 1) * WalSegSz)
-		{
-			pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.endptr),
-						 argv[argc - 1]);
-			goto bad_argument;
+				fd = open_file_in_directory(waldir, fname);
+				if (fd < 0)
+					pg_fatal("could not open file \"%s\"", fname);
+				close(fd);
+
+				/* parse position from file */
+				XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+
+				if (endsegno < segno)
+					pg_fatal("ENDSEG %s is before STARTSEG %s",
+							 argv[optind + 1], argv[optind]);
+
+				if (XLogRecPtrIsInvalid(private.endptr))
+					XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
+											private.endptr);
+
+				/* set segno to endsegno for check of --end */
+				segno = endsegno;
+			}
+
+
+			if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
+				private.endptr != (segno + 1) * WalSegSz)
+			{
+				pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.endptr),
+							 argv[argc - 1]);
+				goto bad_argument;
+			}
 		}
 	}
-	else
-		waldir = identify_target_directory(waldir, NULL);
+	else if (!is_tar)
+		waldir = identify_target_directory(walpath, NULL);
+
+	/* Verify that the archive contains valid WAL files */
+	if (is_tar)
+		verify_tar_archive(&private, waldir, compression);
 
 	/* we don't know what to print */
 	if (XLogRecPtrIsInvalid(private.startptr))
@@ -1211,11 +1430,26 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
+	if (is_tar)
+	{
+		/* Set up for reading tar file */
+		init_tar_archive_reader(&private, waldir, compression);
+
+		/* Routine to decode WAL files in tar archive */
+		routine = XL_ROUTINE(.page_read = TarWALDumpReadPage,
+							 .segment_open = TarWALDumpOpenSegment,
+							 .segment_close = TarWALDumpCloseSegment);
+	}
+	else
+	{
+		/* Routine to decode WAL files */
+		routine = XL_ROUTINE(.page_read = WALDumpReadPage,
+							 .segment_open = WALDumpOpenSegment,
+							 .segment_close = WALDumpCloseSegment);
+	}
+
 	xlogreader_state =
-		XLogReaderAllocate(WalSegSz, waldir,
-						   XL_ROUTINE(.page_read = WALDumpReadPage,
-									  .segment_open = WALDumpOpenSegment,
-									  .segment_close = WALDumpCloseSegment),
+		XLogReaderAllocate(WalSegSz, waldir, routine,
 						   &private);
 	if (!xlogreader_state)
 		pg_fatal("out of memory while allocating a WAL reading processor");
@@ -1325,6 +1559,9 @@ main(int argc, char **argv)
 
 	XLogReaderFree(xlogreader_state);
 
+	if (is_tar)
+		free_tar_archive_reader(&private);
+
 	return EXIT_SUCCESS;
 
 bad_argument:
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 9e62b64ead5..b5d440500de 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -12,6 +12,8 @@
 #define PG_WALDUMP_H
 
 #include "access/xlogdefs.h"
+#include "fe_utils/astreamer.h"
+#include "lib/stringinfo.h"
 
 extern int	WalSegSz;
 
@@ -22,6 +24,23 @@ typedef struct XLogDumpPrivate
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	bool		endptr_reached;
+
+	/* Fields required to read WAL from archive */
+	char	   *archive_name;	/* Tar archive name */
+	int			archive_fd;		/* File descriptor for the open tar file */
+
+	astreamer  *archive_streamer;
+	StringInfo	archive_streamer_buf;	/* Buffer for receiving WAL data */
+	XLogRecPtr	archive_streamer_read_ptr; /* Populate the buffer with records
+											  until this record pointer */
 } XLogDumpPrivate;
 
-#endif		/* end of PG_WALDUMP_H */
+
+extern astreamer *astreamer_waldump_content_new(astreamer *next,
+												XLogRecPtr startptr,
+												XLogRecPtr endptr,
+												XLogDumpPrivate *privateInfo);
+extern int	astreamer_wal_read(char *readBuff, XLogRecPtr startptr, Size count,
+							   XLogDumpPrivate *privateInfo);
+
+#endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 1b712e8d74d..443126a9ce6 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -3,10 +3,13 @@
 
 use strict;
 use warnings FATAL => 'all';
+use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
 
+my $tar = $ENV{TAR};
+
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
 program_options_handling_ok('pg_waldump');
@@ -235,7 +238,7 @@ command_like(
 sub test_pg_waldump
 {
 	local $Test::Builder::Level = $Test::Builder::Level + 1;
-	my @opts = @_;
+	my ($path, @opts) = @_;
 
 	my ($stdout, $stderr);
 
@@ -243,6 +246,7 @@ sub test_pg_waldump
 		'pg_waldump',
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
+		'--path' => $path,
 		@opts
 	  ],
 	  '>' => \$stdout,
@@ -254,11 +258,50 @@ sub test_pg_waldump
 	return @lines;
 }
 
-my @lines;
+# Create a tar archive, sorting the file order
+sub generate_archive
+{
+	my ($archive, $directory, $compression_flags) = @_;
+
+	my @files;
+	opendir my $dh, $directory or die "opendir: $!";
+	while (my $entry = readdir $dh) {
+		# Skip '.' and '..'
+		next if $entry eq '.' || $entry eq '..';
+		push @files, $entry;
+	}
+	closedir $dh;
+
+	@files = sort @files;
+
+	# move into the WAL directory before archiving files
+	my $cwd = getcwd;
+	chdir($directory) || die "chdir: $!";
+	command_ok([$tar, $compression_flags, $archive, @files]);
+	chdir($cwd) || die "chdir: $!";
+}
+
+my $tmp_dir = PostgreSQL::Test::Utils::tempdir_short();
 
 my @scenario = (
 	{
-		'path' => $node->data_dir
+		'path' => $node->data_dir,
+		'is_archive' => 0,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar",
+		'compression_method' => 'none',
+		'compression_flags' => '-cf',
+		'is_archive' => 1,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar.gz",
+		'compression_method' => 'gzip',
+		'compression_flags' => '-czf',
+		'is_archive' => 1,
+		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
 	});
 
 for my $scenario (@scenario)
@@ -267,6 +310,19 @@ for my $scenario (@scenario)
 
 	SKIP:
 	{
+		skip "tar command is not available", 3
+		  if !defined $tar;
+		skip "$scenario->{'compression_method'} compression not supported by this build", 3
+		  if !$scenario->{'enabled'} && $scenario->{'is_archive'};
+
+		  # create pg_wal archive
+		  if ($scenario->{'is_archive'})
+		  {
+			  generate_archive($path,
+				  $node->data_dir . '/pg_wal',
+				  $scenario->{'compression_flags'});
+		  }
+
 		command_fails_like(
 			[ 'pg_waldump', '--path' => $path ],
 			qr/error: no start WAL location given/,
@@ -298,38 +354,42 @@ for my $scenario (@scenario)
 			qr/error: error in WAL record at/,
 			'errors are shown with --quiet');
 
-		@lines = test_pg_waldump('--path' => $path);
+		my @lines;
+		@lines = test_pg_waldump($path);
 		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		@lines = test_pg_waldump($path, '--limit' => 6);
 		is(@lines, 6, 'limit option observed');
 
-		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		@lines = test_pg_waldump($path, '--fullpage');
 		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats');
+		@lines = test_pg_waldump($path, '--stats');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		@lines = test_pg_waldump($path, '--stats=record');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		@lines = test_pg_waldump($path, '--rmgr' => 'Btree');
 		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		@lines = test_pg_waldump($path, '--fork' => 'init');
 		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
 		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
 			0, 'only lines for selected relation');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
 			'--block' => 1);
 		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+
+		# Cleanup.
+		unlink $path if $scenario->{'is_archive'};
 	}
 }
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index a13e8162890..b406ca041ec 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -3444,6 +3444,7 @@ astreamer_recovery_injector
 astreamer_tar_archiver
 astreamer_tar_parser
 astreamer_verify
+astreamer_waldump
 astreamer_zstd_frame
 auth_password_hook_typ
 autovac_table
-- 
2.47.1

From dbacb4b3d19c579eb0e3b8aa2dbbff04c7273584 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Mon, 25 Aug 2025 17:26:29 +0530
Subject: [PATCH v2 6/9] WIP-pg_waldump: Remove the restriction on the order of
 archived WAL files.

With previous patch, pg_waldump would stop decoding if WAL files were
not in the required sequence. With this patch, decoding will now
continue.  Any WAL file that is out of order will be written to a
temporary location, from which it will be read later. Once a temporary
file has been read, it will be removed.

TODO:
  Timeline switching is not handled correctly, especially when a
  timeline change occurs on the next WAL file that was previously
  written to a temporary location.
---
 doc/src/sgml/ref/pg_waldump.sgml       |   8 +-
 src/bin/pg_waldump/astreamer_waldump.c | 189 +++++++++++++++++++++----
 src/bin/pg_waldump/pg_waldump.c        |  77 +++++++++-
 src/bin/pg_waldump/pg_waldump.h        |  26 +++-
 src/bin/pg_waldump/t/001_basic.pl      |   3 +-
 5 files changed, 269 insertions(+), 34 deletions(-)

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index d004bb0f67e..8a28b4f0f91 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -149,8 +149,12 @@ PostgreSQL documentation
         of <envar>PGDATA</envar>.
        </para>
        <para>
-        If a tar archive is provided, its WAL segment files must be in
-        sequential order; otherwise, an error will be reported.
+        If a tar archive is provided and its WAL segment files are not in
+        sequential order, those files will be written to a temporary directory
+        named <filename>pg_waldump_tmp_dir/</filename>. This directory will be
+        created inside the directory specified by the <envar>TMPDIR</envar>
+        environment variable if it is set; otherwise, it will be created within
+        the same directory as the tar archive.
        </para>
       </listitem>
      </varlistentry>
diff --git a/src/bin/pg_waldump/astreamer_waldump.c b/src/bin/pg_waldump/astreamer_waldump.c
index 916d388ef0c..acfbace7502 100644
--- a/src/bin/pg_waldump/astreamer_waldump.c
+++ b/src/bin/pg_waldump/astreamer_waldump.c
@@ -18,8 +18,8 @@
 
 #include "access/xlog_internal.h"
 #include "access/xlogdefs.h"
+#include "common/file_perm.h"
 #include "common/logging.h"
-#include "fe_utils/simple_list.h"
 #include "pg_waldump.h"
 
 /*
@@ -37,6 +37,8 @@ typedef struct astreamer_waldump
 
 	/* These fields change with archive member. */
 	bool		skipThisSeg;
+	bool		writeThisSeg;
+	FILE	   *segFp;
 	XLogSegNo	nextSegNo;		/* Next expected segment to stream */
 } astreamer_waldump;
 
@@ -53,8 +55,15 @@ static bool member_is_relevant_wal(astreamer_member *member,
 								   XLogSegNo startSegNo,
 								   XLogSegNo endSegNo,
 								   XLogSegNo nextSegNo,
+								   char **curFname,
 								   XLogSegNo *curSegNo,
 								   TimeLineID *curSegTimeline);
+static FILE *member_prepare_tmp_write(XLogSegNo curSegNo,
+									  const char *fname,
+									  XLogDumpPrivate *privateInfo);
+static XLogSegNo member_next_segno(XLogSegNo curSegNo,
+								   TimeLineID timeline,
+								   XLogDumpPrivate *privateInfo);
 
 static const astreamer_ops astreamer_waldump_ops = {
 	.content = astreamer_waldump_content,
@@ -189,17 +198,8 @@ astreamer_waldump_content_new(astreamer *next, XLogRecPtr startptr,
 	if (XLogRecPtrIsInvalid(startptr))
 		streamer->startSegNo = 0;
 	else
-	{
 		XLByteToSeg(startptr, streamer->startSegNo, WalSegSz);
 
-		/*
-		 * Initialize the record pointer to the beginning of the first
-		 * segment; this pointer will track the WAL record reading status.
-		 */
-		XLogSegNoOffsetToRecPtr(streamer->startSegNo, 0, WalSegSz,
-								privateInfo->archive_streamer_read_ptr);
-	}
-
 	if (XLogRecPtrIsInvalid(endPtr))
 		streamer->endSegNo = UINT64_MAX;
 	else
@@ -228,19 +228,21 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 	{
 		case ASTREAMER_MEMBER_HEADER:
 			{
+				char	   *fname;
 				XLogSegNo	segNo;
 				TimeLineID	timeline;
 
 				pg_log_debug("pg_waldump: reading \"%s\"", member->pathname);
 
 				mystreamer->skipThisSeg = false;
+				mystreamer->writeThisSeg = false;
 
 				if (!member_is_relevant_wal(member,
 											privateInfo->timeline,
 											mystreamer->startSegNo,
 											mystreamer->endSegNo,
 											mystreamer->nextSegNo,
-											&segNo, &timeline))
+											&fname, &segNo, &timeline))
 				{
 					mystreamer->skipThisSeg = true;
 					break;
@@ -254,24 +256,38 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 				if (mystreamer->nextSegNo == 0)
 					break;
 
-				/* WAL segments must be archived in order */
+				/*
+				 * When WAL segments are not archived sequentially, it becomes
+				 * necessary to write out (or preserve) segments that might be
+				 * required at a later point.
+				 */
 				if (mystreamer->nextSegNo != segNo)
 				{
-					pg_log_error("WAL files are not archived in sequential order");
-					pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
-										mystreamer->nextSegNo, segNo);
-					exit(1);
+					mystreamer->writeThisSeg = true;
+					mystreamer->segFp =
+						member_prepare_tmp_write(segNo, fname, privateInfo);
+					break;
 				}
 
 				/*
-				 * We track the reading of WAL segment records using a pointer
-				 * that's continuously incremented by the length of the
-				 * received data. This pointer is crucial for serving WAL page
-				 * requests from the WAL decoding routine, so it must be
-				 * accurate.
+				 * We are now streaming segment containt.
+				 *
+				 * We need to track the reading of WAL segment records using a
+				 * pointer that's typically incremented by the length of the
+				 * data read. However, we sometimes export the WAL file to
+				 * temporary storage, allowing the decoding routine to read
+				 * directly from there. This makes continuous pointer
+				 * incrementing challenging, as file reads can occur from any
+				 * offset, leading to potential errors. Therefore, we now
+				 * reset the pointer when reading from a file for streaming.
+				 * Also, if there's any existing data in the buffer, the next
+				 * WAL record should logically follow it.
 				 */
 #ifdef USE_ASSERT_CHECKING
-				if (mystreamer->nextSegNo != 0)
+				Assert(!mystreamer->skipThisSeg);
+				Assert(!mystreamer->writeThisSeg);
+
+				if (privateInfo->archive_streamer_buf->len != 0)
 				{
 					XLogRecPtr	recPtr;
 
@@ -280,11 +296,19 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 				}
 #endif
 
+				/*
+				 * Initialized to the beginning of the current segment being
+				 * streamed through the buffer.
+				 */
+				XLogSegNoOffsetToRecPtr(segNo, 0, WalSegSz,
+										privateInfo->archive_streamer_read_ptr);
+
 				/* Save the timeline */
 				privateInfo->timeline = timeline;
 
 				/* Update the next expected segment number */
-				mystreamer->nextSegNo += 1;
+				mystreamer->nextSegNo =
+					member_next_segno(segNo, timeline, privateInfo);
 			}
 			break;
 
@@ -293,12 +317,44 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 			if (mystreamer->skipThisSeg)
 				break;
 
+			/* Or, write contents to file */
+			if (mystreamer->writeThisSeg)
+			{
+				Assert(mystreamer->segFp != NULL);
+
+				errno = 0;
+				if (len > 0 && fwrite(data, len, 1, mystreamer->segFp) != 1)
+				{
+					char	   *fname;
+					int			pathlen = strlen(member->pathname);
+
+					Assert(pathlen >= XLOG_FNAME_LEN);
+
+					fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+
+					/*
+					 * If write didn't set errno, assume problem is no disk
+					 * space
+					 */
+					if (errno == 0)
+						errno = ENOSPC;
+					pg_fatal("could not write to file \"%s/%s\": %m",
+							 privateInfo->tmpdir, fname);
+				}
+				break;
+			}
+
 			/* Or, copy contents to buffer */
 			privateInfo->archive_streamer_read_ptr += len;
 			astreamer_buffer_bytes(streamer, &data, &len, len);
 			break;
 
 		case ASTREAMER_MEMBER_TRAILER:
+			if (mystreamer->segFp != NULL)
+			{
+				fclose(mystreamer->segFp);
+				mystreamer->segFp = NULL;
+			}
 			break;
 
 		case ASTREAMER_ARCHIVE_TRAILER:
@@ -325,8 +381,14 @@ astreamer_waldump_finalize(astreamer *streamer)
 static void
 astreamer_waldump_free(astreamer *streamer)
 {
+	astreamer_waldump *mystreamer;
+
 	Assert(streamer->bbs_next == NULL);
 
+	mystreamer = (astreamer_waldump *) streamer;
+	if (mystreamer->segFp != NULL)
+		fclose(mystreamer->segFp);
+
 	pfree(streamer->bbs_buffer.data);
 	pfree(streamer);
 }
@@ -339,8 +401,8 @@ astreamer_waldump_free(astreamer *streamer)
 static bool
 member_is_relevant_wal(astreamer_member *member, TimeLineID startTimeLineID,
 					   XLogSegNo startSegNo, XLogSegNo endSegNo,
-					   XLogSegNo nextSegNo, XLogSegNo *curSegNo,
-					   TimeLineID *curSegTimeline)
+					   XLogSegNo nextSegNo, char **curFname,
+					   XLogSegNo *curSegNo, TimeLineID *curSegTimeline)
 {
 	int			pathlen;
 	XLogSegNo	segNo;
@@ -371,8 +433,85 @@ member_is_relevant_wal(astreamer_member *member, TimeLineID startTimeLineID,
 	if (startSegNo > segNo || endSegNo < segNo)
 		return false;
 
+	*curFname = fname;
 	*curSegNo = segNo;
 	*curSegTimeline = timeline;
 
 	return true;
 }
+
+/*
+ * Create an empty placeholder file and return its handle.  The file is also
+ * added to an exported list for future management, e.g.  access, deletion, and
+ * existence checks.
+ */
+static FILE *
+member_prepare_tmp_write(XLogSegNo curSegNo, const char *fname,
+						 XLogDumpPrivate *privateInfo)
+{
+	FILE	   *file;
+	char	   *fpath = get_tmp_wal_file_path(privateInfo, fname);
+
+	/* Create an empty placeholder */
+	file = fopen(fpath, PG_BINARY_W);
+	if (file == NULL)
+		pg_fatal("could not create file \"%s\": %m", fpath);
+
+#ifndef WIN32
+	if (chmod(fpath, pg_file_create_mode))
+		pg_fatal("could not set permissions on file \"%s\": %m",
+				 fpath);
+#endif
+
+	/* Record this segment's export */
+	simple_string_list_append(&privateInfo->exportedSegList, fname);
+	pfree(fpath);
+
+	return file;
+}
+
+/*
+ * Get next WAL segment that needs to be retrieved from the archive.
+ *
+ * The function checks for the presence of a previously read and extracted WAL
+ * segment in the temporary storage. If a temporary file is found for that
+ * segment, it indicates the segment has already been successfully retrieved
+ * from the archive. In this case, the function increments the segment number
+ * and repeats the check. This process continues until a segment that has not
+ * yet been retrieved is found, at which point the function returns its number.
+ */
+static XLogSegNo
+member_next_segno(XLogSegNo curSegNo, TimeLineID timeline,
+				  XLogDumpPrivate *privateInfo)
+{
+	XLogSegNo	nextSegNo = curSegNo + 1;
+	bool		exists;
+
+	/*
+	 * If we find a file that was previously written to the temporary space,
+	 * it indicates that the corresponding WAL segment request has already
+	 * been fulfilled. In that case, we increment the nextSegNo counter and
+	 * check again whether that segment number again. if found above steps
+	 * will be return if not then we return that segment number which would be
+	 * needed from the archive.
+	 */
+	do
+	{
+		char		fname[MAXFNAMELEN];
+
+		XLogFileName(fname, timeline, nextSegNo, WalSegSz);
+
+		/*
+		 * If the WAL segment has already been exported, increment the counter
+		 * and check for the next segment.
+		 */
+		exists = false;
+		if (simple_string_list_member(&privateInfo->exportedSegList, fname))
+		{
+			nextSegNo += 1;
+			exists = true;
+		}
+	} while (exists);
+
+	return nextSegNo;
+}
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 64f3a65b735..d456adce59c 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -393,13 +393,14 @@ setup_astreamer(XLogDumpPrivate *private, pg_compress_algorithm compression,
 }
 
 /*
- * Initializes the archive reader for a tar file.
+ * Initializes the tar archive reader and a temporary directory for WAL files.
  */
 static void
 init_tar_archive_reader(XLogDumpPrivate *private, char *waldir,
 						pg_compress_algorithm compression)
 {
 	int			fd;
+	char	   *tmpdir;
 
 	/* Now, the tar archive and store its file descriptor */
 	fd = open_file_in_directory(waldir, private->archive_name);
@@ -411,6 +412,15 @@ init_tar_archive_reader(XLogDumpPrivate *private, char *waldir,
 
 	/* Setup tar archive reading facility */
 	setup_astreamer(private, compression, private->startptr, private->endptr);
+
+	/* Temporary space for writing WAL segments */
+	if (getenv("TMPDIR"))
+		tmpdir = pstrdup(getenv("TMPDIR"));
+	else
+		tmpdir = waldir != NULL ? pstrdup(waldir) : pstrdup(".");
+	canonicalize_path(tmpdir);
+
+	private->tmpdir = tmpdir;
 }
 
 /*
@@ -419,6 +429,8 @@ init_tar_archive_reader(XLogDumpPrivate *private, char *waldir,
 static void
 free_tar_archive_reader(XLogDumpPrivate *private)
 {
+	SimpleStringListCell *cell;
+
 	/*
 	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
 	 * flush any remaining buffered data or to ensure the end of the tar
@@ -432,6 +444,15 @@ free_tar_archive_reader(XLogDumpPrivate *private)
 	if (close(private->archive_fd) != 0)
 		pg_log_error("could not close file \"%s\": %m",
 					 private->archive_name);
+
+	/* Clear out any existing temporary files */
+	for (cell = private->exportedSegList.head; cell; cell = cell->next)
+	{
+		char	   *fpath = get_tmp_wal_file_path(private, cell->val);
+
+		unlink(fpath);
+		pfree(fpath);
+	}
 }
 
 /*
@@ -559,7 +580,7 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = required_read_len(private, targetPtr, reqLen);
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
 	if (private->endptr_reached)
@@ -618,12 +639,60 @@ TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				   XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = required_read_len(private, targetPtr, reqLen);
+	int			count = required_read_len(private, targetPagePtr, reqLen);
+	XLogSegNo	nextSegNo;
 
 	if (private->endptr_reached)
 		return -1;
 
-	/* Read the WAL page from the archive streamer */
+	/*
+	 * If the target page is in a different segment, first check for the WAL
+	 * segment's physical existence in the temporary directory.
+	 *
+	 * XXX: Timeline change is not handled.
+	 */
+	nextSegNo = state->seg.ws_segno;
+	if (!XLByteInSeg(targetPagePtr, nextSegNo, WalSegSz))
+	{
+		char		fname[MAXPGPATH];
+		char	   *fpath;
+
+		if (state->seg.ws_file >= 0)
+		{
+			close(state->seg.ws_file);
+			state->seg.ws_file = -1;
+
+			/* Remove this file, as it is no longer needed. */
+			XLogFileName(fname, state->seg.ws_tli, nextSegNo, WalSegSz);
+			fpath = get_tmp_wal_file_path(private, fname);
+			unlink(fpath);
+			pfree(fpath);
+		}
+
+		XLByteToSeg(targetPagePtr, nextSegNo, WalSegSz);
+		state->seg.ws_tli = private->timeline;
+		state->seg.ws_segno = nextSegNo;
+
+		/*
+		 * If the next segment exists, open it and continue reading from there
+		 */
+		XLogFileName(fname, private->timeline, nextSegNo, WalSegSz);
+		if (simple_string_list_member(&private->exportedSegList, fname))
+		{
+			fpath = get_tmp_wal_file_path(private, fname);
+			state->seg.ws_file = open(fpath, O_RDONLY | PG_BINARY, 0);
+
+			if (state->seg.ws_file < 0)
+				pg_fatal("could not open file \"%s\": %m", fpath);
+		}
+	}
+
+	/* Continue reading from the open WAL segment, if any */
+	if (state->seg.ws_file >= 0)
+		return WALDumpReadPage(state, targetPagePtr, reqLen, targetPtr,
+							   readBuff);
+
+	/* Otherwise, read the WAL page from the archive streamer */
 	return astreamer_wal_read(readBuff, targetPagePtr, count, private);
 }
 
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index b5d440500de..614e679cb96 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -13,8 +13,11 @@
 
 #include "access/xlogdefs.h"
 #include "fe_utils/astreamer.h"
+#include "fe_utils/simple_list.h"
 #include "lib/stringinfo.h"
 
+#define TEMP_FILE_EXT	"waldump.tmp"
+
 extern int	WalSegSz;
 
 /* Contains the necessary information to drive WAL decoding */
@@ -31,11 +34,30 @@ typedef struct XLogDumpPrivate
 
 	astreamer  *archive_streamer;
 	StringInfo	archive_streamer_buf;	/* Buffer for receiving WAL data */
-	XLogRecPtr	archive_streamer_read_ptr; /* Populate the buffer with records
-											  until this record pointer */
+	XLogRecPtr	archive_streamer_read_ptr;	/* Populate the buffer with
+											 * records until this record
+											 * pointer */
+	char	   *tmpdir;			/* Temporary direcotry to export file */
+	SimpleStringList exportedSegList;	/* Temporary exported WAL file list */
 } XLogDumpPrivate;
 
 
+/*
+ * Generate the temporary WAL file path.
+ *
+ * Note that the caller is responsible to pfree it.
+ */
+static inline char *
+get_tmp_wal_file_path(XLogDumpPrivate *privateInfo, const char *fname)
+{
+	char	   *fpath = (char *) palloc(MAXPGPATH);
+
+	snprintf(fpath, MAXPGPATH, "%s/%s.%s", privateInfo->tmpdir, fname,
+			 TEMP_FILE_EXT);
+
+	return fpath;
+}
+
 extern astreamer *astreamer_waldump_content_new(astreamer *next,
 												XLogRecPtr startptr,
 												XLogRecPtr endptr,
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 443126a9ce6..d5fa1f6d28d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -7,6 +7,7 @@ use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
+use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
 
@@ -272,7 +273,7 @@ sub generate_archive
 	}
 	closedir $dh;
 
-	@files = sort @files;
+	@files = shuffle @files;
 
 	# move into the WAL directory before archiving files
 	my $cwd = getcwd;
-- 
2.47.1

From 64dbdfaa575749b76ebdd3fd235a8186b6eb19fc Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 14:47:43 +0530
Subject: [PATCH v2 7/9] pg_verifybackup: Delay default WAL directory
 preparation.

We are not sure whether to parse WAL from a directory or an archive
until the backup format is known. Therefore, we delay preparing the
default WAL directory until the point of parsing. This delay is
harmless, as the WAL directory is not used elsewhere.
---
 src/bin/pg_verifybackup/pg_verifybackup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 5e6c13bb921..31ebc1581fb 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -285,10 +285,6 @@ main(int argc, char **argv)
 		manifest_path = psprintf("%s/backup_manifest",
 								 context.backup_directory);
 
-	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
-
 	/*
 	 * Try to read the manifest. We treat any errors encountered while parsing
 	 * the manifest as fatal; there doesn't seem to be much point in trying to
@@ -368,6 +364,10 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
+	/* By default, look for the WAL in the backup directory, too. */
+	if (wal_directory == NULL)
+		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
-- 
2.47.1

From b48d5a7ed121c694273ad8cf2c3c78aa4ae23b1d Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 24 Jun 2025 11:33:20 +0530
Subject: [PATCH v3 1/8] Refactor: pg_waldump: Move some declarations to new
 pg_waldump.h

This is in preparation for adding a second source file to this
directory.
---
 src/bin/pg_waldump/pg_waldump.c | 11 ++---------
 src/bin/pg_waldump/pg_waldump.h | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 9 deletions(-)
 create mode 100644 src/bin/pg_waldump/pg_waldump.h

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 13d3ec2f5be..a49b2fd96c7 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -29,6 +29,7 @@
 #include "common/logging.h"
 #include "common/relpath.h"
 #include "getopt_long.h"
+#include "pg_waldump.h"
 #include "rmgrdesc.h"
 #include "storage/bufpage.h"
 
@@ -39,19 +40,11 @@
 
 static const char *progname;
 
-static int	WalSegSz;
+int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 static volatile sig_atomic_t time_to_stop = false;
 
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
-typedef struct XLogDumpPrivate
-{
-	TimeLineID	timeline;
-	XLogRecPtr	startptr;
-	XLogRecPtr	endptr;
-	bool		endptr_reached;
-} XLogDumpPrivate;
-
 typedef struct XLogDumpConfig
 {
 	/* display options */
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
new file mode 100644
index 00000000000..9e62b64ead5
--- /dev/null
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -0,0 +1,27 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_waldump.h - decode and display WAL
+ *
+ * Copyright (c) 2013-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  src/bin/pg_waldump/pg_waldump.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_WALDUMP_H
+#define PG_WALDUMP_H
+
+#include "access/xlogdefs.h"
+
+extern int	WalSegSz;
+
+/* Contains the necessary information to drive WAL decoding */
+typedef struct XLogDumpPrivate
+{
+	TimeLineID	timeline;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
+	bool		endptr_reached;
+} XLogDumpPrivate;
+
+#endif		/* end of PG_WALDUMP_H */
-- 
2.47.1

From c42fad18faa0016eee4e2eee2e4d0d465156a787 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 26 Jun 2025 11:42:53 +0530
Subject: [PATCH v3 2/8] Refactor: pg_waldump: Separate logic used to calculate
 the required read size.

This refactoring prepares the codebase for an upcoming patch that will
support reading WAL from tar files. The logic for calculating the
required read size has been updated to handle both normal WAL files
and WAL files located inside a tar archive.
---
 src/bin/pg_waldump/pg_waldump.c | 39 ++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index a49b2fd96c7..8d0cd9e7156 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -326,6 +326,29 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/* Returns the size in bytes of the data to be read. */
+static inline int
+required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
+				  int reqLen)
+{
+	int			count = XLOG_BLCKSZ;
+
+	if (private->endptr != InvalidXLogRecPtr)
+	{
+		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
+			count = XLOG_BLCKSZ;
+		else if (targetPagePtr + reqLen <= private->endptr)
+			count = private->endptr - targetPagePtr;
+		else
+		{
+			private->endptr_reached = true;
+			return -1;
+		}
+	}
+
+	return count;
+}
+
 /* pg_waldump's XLogReaderRoutine->segment_open callback */
 static void
 WALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
@@ -383,21 +406,11 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = XLOG_BLCKSZ;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
-	if (private->endptr != InvalidXLogRecPtr)
-	{
-		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
-			count = XLOG_BLCKSZ;
-		else if (targetPagePtr + reqLen <= private->endptr)
-			count = private->endptr - targetPagePtr;
-		else
-		{
-			private->endptr_reached = true;
-			return -1;
-		}
-	}
+	if (private->endptr_reached)
+		return -1;
 
 	if (!WALRead(state, readBuff, targetPagePtr, count, private->timeline,
 				 &errinfo))
-- 
2.47.1

From 31c4a7d8d6a24892e5c8bb476ea5665e15d93aec Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 30 Jul 2025 12:43:30 +0530
Subject: [PATCH v3 3/8] Refactor: pg_waldump: Restructure TAP tests.

Restructured some tests to run inside a loop, facilitating their
re-execution for decoding WAL from tar archives.
---
 src/bin/pg_waldump/t/001_basic.pl | 123 ++++++++++++++++--------------
 1 file changed, 67 insertions(+), 56 deletions(-)

diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index f26d75e01cf..1b712e8d74d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -198,28 +198,6 @@ command_like(
 	],
 	qr/./,
 	'runs with start and end segment specified');
-command_fails_like(
-	[ 'pg_waldump', '--path' => $node->data_dir ],
-	qr/error: no start WAL location given/,
-	'path option requires start location');
-command_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-		'--end' => $end_lsn,
-	],
-	qr/./,
-	'runs with path option and start and end locations');
-command_fails_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-	],
-	qr/error: error in WAL record at/,
-	'falling off the end of the WAL results in an error');
-
 command_like(
 	[
 		'pg_waldump', '--quiet',
@@ -227,15 +205,6 @@ command_like(
 	],
 	qr/^$/,
 	'no output with --quiet option');
-command_fails_like(
-	[
-		'pg_waldump', '--quiet',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn
-	],
-	qr/error: error in WAL record at/,
-	'errors are shown with --quiet');
-
 
 # Test for: Display a message that we're skipping data if `from`
 # wasn't a pointer to the start of a record.
@@ -272,7 +241,6 @@ sub test_pg_waldump
 
 	my $result = IPC::Run::run [
 		'pg_waldump',
-		'--path' => $node->data_dir,
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
 		@opts
@@ -288,38 +256,81 @@ sub test_pg_waldump
 
 my @lines;
 
-@lines = test_pg_waldump;
-is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
+my @scenario = (
+	{
+		'path' => $node->data_dir
+	});
 
-@lines = test_pg_waldump('--limit' => 6);
-is(@lines, 6, 'limit option observed');
+for my $scenario (@scenario)
+{
+	my $path = $scenario->{'path'};
 
-@lines = test_pg_waldump('--fullpage');
-is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
+	SKIP:
+	{
+		command_fails_like(
+			[ 'pg_waldump', '--path' => $path ],
+			qr/error: no start WAL location given/,
+			'path option requires start location');
+		command_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+				'--end' => $end_lsn,
+			],
+			qr/./,
+			'runs with path option and start and end locations');
+		command_fails_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+			],
+			qr/error: error in WAL record at/,
+			'falling off the end of the WAL results in an error');
 
-@lines = test_pg_waldump('--stats');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		command_fails_like(
+			[
+				'pg_waldump', '--quiet',
+				'--path' => $path,
+				'--start' => $start_lsn
+			],
+			qr/error: error in WAL record at/,
+			'errors are shown with --quiet');
 
-@lines = test_pg_waldump('--stats=record');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		@lines = test_pg_waldump('--path' => $path);
+		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-@lines = test_pg_waldump('--rmgr' => 'Btree');
-is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		is(@lines, 6, 'limit option observed');
 
-@lines = test_pg_waldump('--fork' => 'init');
-is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
-is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
-	0, 'only lines for selected relation');
+		@lines = test_pg_waldump('--path' => $path, '--stats');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
-	'--block' => 1);
-is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
+		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+
+		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
+		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
+			0, 'only lines for selected relation');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
+			'--block' => 1);
+		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+	}
+}
 
 done_testing();
-- 
2.47.1

From f15b7e6d33e107cb141586af6072b41266eff0eb Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 18:37:59 +0530
Subject: [PATCH v3 4/8] pg_waldump: Add support for archived WAL decoding.

pg_waldump can now accept the path to a tar archive containing WAL
files and decode them. This feature was added primarily for
pg_verifybackup, which previously disabled WAL parsing for
tar-formatted backups.

Note that this patch requires that the WAL files within the archive be
in sequential order; an error will be reported otherwise. The next
patch is planned to remove this restriction.
---
 doc/src/sgml/ref/pg_waldump.sgml       |   8 +-
 src/bin/pg_waldump/Makefile            |   7 +-
 src/bin/pg_waldump/astreamer_waldump.c | 378 +++++++++++++++++++++++++
 src/bin/pg_waldump/meson.build         |   4 +-
 src/bin/pg_waldump/pg_waldump.c        | 362 +++++++++++++++++++----
 src/bin/pg_waldump/pg_waldump.h        |  21 +-
 src/bin/pg_waldump/t/001_basic.pl      |  84 +++++-
 src/tools/pgindent/typedefs.list       |   1 +
 8 files changed, 787 insertions(+), 78 deletions(-)
 create mode 100644 src/bin/pg_waldump/astreamer_waldump.c

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index ce23add5577..d004bb0f67e 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -141,13 +141,17 @@ PostgreSQL documentation
       <term><option>--path=<replaceable>path</replaceable></option></term>
       <listitem>
        <para>
-        Specifies a directory to search for WAL segment files or a
-        directory with a <literal>pg_wal</literal> subdirectory that
+        Specifies a tar archive or a directory to search for WAL segment files
+        or a directory with a <literal>pg_wal</literal> subdirectory that
         contains such files.  The default is to search in the current
         directory, the <literal>pg_wal</literal> subdirectory of the
         current directory, and the <literal>pg_wal</literal> subdirectory
         of <envar>PGDATA</envar>.
        </para>
+       <para>
+        If a tar archive is provided, its WAL segment files must be in
+        sequential order; otherwise, an error will be reported.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index 4c1ee649501..b234613eb50 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -3,6 +3,9 @@
 PGFILEDESC = "pg_waldump - decode and display WAL"
 PGAPPICON=win32
 
+# make these available to TAP test scripts
+export TAR
+
 subdir = src/bin/pg_waldump
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
@@ -12,11 +15,13 @@ OBJS = \
 	$(WIN32RES) \
 	compat.o \
 	pg_waldump.o \
+	astreamer_waldump.o \
 	rmgrdesc.o \
 	xlogreader.o \
 	xlogstats.o
 
-override CPPFLAGS := -DFRONTEND $(CPPFLAGS)
+override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
diff --git a/src/bin/pg_waldump/astreamer_waldump.c b/src/bin/pg_waldump/astreamer_waldump.c
new file mode 100644
index 00000000000..61876e834a9
--- /dev/null
+++ b/src/bin/pg_waldump/astreamer_waldump.c
@@ -0,0 +1,378 @@
+/*-------------------------------------------------------------------------
+ *
+ * astreamer_waldump.c
+ *		A generic facility for reading WAL data from tar archives via archive
+ *		streamer.
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/bin/pg_waldump/astreamer_waldump.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <unistd.h>
+
+#include "access/xlog_internal.h"
+#include "access/xlogdefs.h"
+#include "common/logging.h"
+#include "fe_utils/simple_list.h"
+#include "pg_waldump.h"
+
+/*
+ * How many bytes should we try to read from a file at once?
+ */
+#define READ_CHUNK_SIZE				(128 * 1024)
+
+typedef struct astreamer_waldump
+{
+	/* These fields don't change once initialized. */
+	astreamer	base;
+	XLogSegNo	startSegNo;
+	XLogSegNo	endSegNo;
+	XLogDumpPrivate *privateInfo;
+
+	/* These fields change with archive member. */
+	bool		skipThisSeg;
+	XLogSegNo	nextSegNo;		/* Next expected segment to stream */
+} astreamer_waldump;
+
+static int	astreamer_archive_read(XLogDumpPrivate *privateInfo);
+static void astreamer_waldump_content(astreamer *streamer,
+									  astreamer_member *member,
+									  const char *data, int len,
+									  astreamer_archive_context context);
+static void astreamer_waldump_finalize(astreamer *streamer);
+static void astreamer_waldump_free(astreamer *streamer);
+
+static bool member_is_relevant_wal(astreamer_member *member,
+								   TimeLineID startTimeLineID,
+								   XLogSegNo startSegNo,
+								   XLogSegNo endSegNo,
+								   XLogSegNo nextSegNo,
+								   XLogSegNo *curSegNo,
+								   TimeLineID *curSegTimeline);
+
+static const astreamer_ops astreamer_waldump_ops = {
+	.content = astreamer_waldump_content,
+	.finalize = astreamer_waldump_finalize,
+	.free = astreamer_waldump_free
+};
+
+/*
+ * Copies WAL data from astreamer to readBuff; if unavailable, fetches more
+ * from the tar archive via astreamer.
+ */
+int
+astreamer_wal_read(char *readBuff, XLogRecPtr targetPagePtr, Size count,
+				   XLogDumpPrivate *privateInfo)
+{
+	char	   *p = readBuff;
+	Size		nbytes = count;
+	XLogRecPtr	recptr = targetPagePtr;
+	volatile StringInfo astreamer_buf = privateInfo->archive_streamer_buf;
+
+	while (nbytes > 0)
+	{
+		char	   *buf = astreamer_buf->data;
+		int			len = astreamer_buf->len;
+
+		/* WAL record range that the buffer contains */
+		XLogRecPtr	endPtr = privateInfo->archive_streamer_read_ptr;
+		XLogRecPtr	startPtr = (endPtr > len) ? endPtr - len : 0;
+
+		/*
+		 * Ignore existing data if the required target page has not yet been
+		 * read.
+		 */
+		if (recptr >= endPtr)
+		{
+			len = 0;
+
+			/* Reset the buffer */
+			resetStringInfo(astreamer_buf);
+		}
+
+		if (len > 0 && recptr > startPtr)
+		{
+			int			skipBytes = 0;
+
+			/*
+			 * The required offset is not at the start of the archive streamer
+			 * buffer, so skip bytes until reaching the desired offset of the
+			 * target page.
+			 */
+			skipBytes = recptr - startPtr;
+
+			buf += skipBytes;
+			len -= skipBytes;
+		}
+
+		if (len > 0)
+		{
+			int			readBytes = len >= nbytes ? nbytes : len;
+
+			/*
+			 * Ensure we are reading the correct page, unless we've received
+			 * an invalid record pointer. In that specific case, it's
+			 * acceptable to read any page.
+			 */
+			Assert(XLogRecPtrIsInvalid(recptr) ||
+				   (recptr >= startPtr && recptr < endPtr));
+
+			memcpy(p, buf, readBytes);
+
+			/* Update state for read */
+			nbytes -= readBytes;
+			p += readBytes;
+			recptr += readBytes;
+		}
+		else
+		{
+			/* Fetch more data */
+			if (astreamer_archive_read(privateInfo) == 0)
+				break;			/* No data remaining */
+		}
+	}
+
+	return (count - nbytes) ? (count - nbytes) : -1;
+}
+
+/*
+ * Reads the archive and passes it to the archive streamer for decompression.
+ */
+static int
+astreamer_archive_read(XLogDumpPrivate *privateInfo)
+{
+	int			rc;
+	char	   *buffer;
+
+	buffer = pg_malloc(READ_CHUNK_SIZE * sizeof(uint8));
+
+	/* Read more data from the tar file */
+	rc = read(privateInfo->archive_fd, buffer, READ_CHUNK_SIZE);
+	if (rc < 0)
+		pg_fatal("could not read file \"%s\": %m",
+				 privateInfo->archive_name);
+
+	/*
+	 * Decrypt (if required), and then parse the previously read contents of
+	 * the tar file.
+	 */
+	if (rc > 0)
+		astreamer_content(privateInfo->archive_streamer, NULL,
+						  buffer, rc, ASTREAMER_UNKNOWN);
+	pg_free(buffer);
+
+	return rc;
+}
+
+/*
+ * Create an astreamer that can read WAL from tar file.
+ */
+astreamer *
+astreamer_waldump_content_new(astreamer *next, XLogRecPtr startptr,
+							  XLogRecPtr endPtr, XLogDumpPrivate *privateInfo)
+{
+	astreamer_waldump *streamer;
+
+	streamer = palloc0(sizeof(astreamer_waldump));
+	*((const astreamer_ops **) &streamer->base.bbs_ops) =
+		&astreamer_waldump_ops;
+
+	streamer->base.bbs_next = next;
+	initStringInfo(&streamer->base.bbs_buffer);
+
+	if (XLogRecPtrIsInvalid(startptr))
+		streamer->startSegNo = 0;
+	else
+	{
+		XLByteToSeg(startptr, streamer->startSegNo, WalSegSz);
+
+		/*
+		 * Initialize the record pointer to the beginning of the first
+		 * segment; this pointer will track the WAL record reading status.
+		 */
+		XLogSegNoOffsetToRecPtr(streamer->startSegNo, 0, WalSegSz,
+								privateInfo->archive_streamer_read_ptr);
+	}
+
+	if (XLogRecPtrIsInvalid(endPtr))
+		streamer->endSegNo = UINT64_MAX;
+	else
+		XLByteToSeg(endPtr, streamer->endSegNo, WalSegSz);
+
+	streamer->nextSegNo = streamer->startSegNo;
+	streamer->privateInfo = privateInfo;
+
+	return &streamer->base;
+}
+
+/*
+ * Main entry point of the archive streamer for reading WAL from a tar file.
+ */
+static void
+astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
+						  const char *data, int len,
+						  astreamer_archive_context context)
+{
+	astreamer_waldump *mystreamer = (astreamer_waldump *) streamer;
+	XLogDumpPrivate *privateInfo = mystreamer->privateInfo;
+
+	Assert(context != ASTREAMER_UNKNOWN);
+
+	switch (context)
+	{
+		case ASTREAMER_MEMBER_HEADER:
+			{
+				XLogSegNo	segNo;
+				TimeLineID	timeline;
+
+				pg_log_debug("pg_waldump: reading \"%s\"", member->pathname);
+
+				mystreamer->skipThisSeg = false;
+
+				if (!member_is_relevant_wal(member,
+											privateInfo->timeline,
+											mystreamer->startSegNo,
+											mystreamer->endSegNo,
+											mystreamer->nextSegNo,
+											&segNo, &timeline))
+				{
+					mystreamer->skipThisSeg = true;
+					break;
+				}
+
+				/*
+				 * If nextSegNo is 0, the check is skipped, and any WAL file
+				 * can be read -- this typically occurs during initial
+				 * verification.
+				 */
+				if (mystreamer->nextSegNo == 0)
+					break;
+
+				/* WAL segments must be archived in order */
+				if (mystreamer->nextSegNo != segNo)
+				{
+					pg_log_error("WAL files are not archived in sequential order");
+					pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
+										mystreamer->nextSegNo, segNo);
+					exit(1);
+				}
+
+				/*
+				 * We track the reading of WAL segment records using a pointer
+				 * that's continuously incremented by the length of the
+				 * received data. This pointer is crucial for serving WAL page
+				 * requests from the WAL decoding routine, so it must be
+				 * accurate.
+				 */
+#ifdef USE_ASSERT_CHECKING
+				if (mystreamer->nextSegNo != 0)
+				{
+					XLogRecPtr	recPtr;
+
+					XLogSegNoOffsetToRecPtr(segNo, 0, WalSegSz, recPtr);
+					Assert(privateInfo->archive_streamer_read_ptr == recPtr);
+				}
+#endif
+
+				/* Save the timeline */
+				privateInfo->timeline = timeline;
+
+				/* Update the next expected segment number */
+				mystreamer->nextSegNo += 1;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_CONTENTS:
+			/* Skip this segment */
+			if (mystreamer->skipThisSeg)
+				break;
+
+			/* Or, copy contents to buffer */
+			privateInfo->archive_streamer_read_ptr += len;
+			astreamer_buffer_bytes(streamer, &data, &len, len);
+			break;
+
+		case ASTREAMER_MEMBER_TRAILER:
+			break;
+
+		case ASTREAMER_ARCHIVE_TRAILER:
+			break;
+
+		default:
+			/* Shouldn't happen. */
+			pg_fatal("unexpected state while parsing tar file");
+	}
+}
+
+/*
+ * End-of-stream processing for a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_finalize(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+}
+
+/*
+ * Free memory associated with a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_free(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+
+	pfree(streamer->bbs_buffer.data);
+	pfree(streamer);
+}
+
+/*
+ * Returns true if the archive member name matches the WAL naming format and
+ * the corresponding WAL segment falls within the WAL decoding target range;
+ * otherwise, returns false.
+ */
+static bool
+member_is_relevant_wal(astreamer_member *member, TimeLineID startTimeLineID,
+					   XLogSegNo startSegNo, XLogSegNo endSegNo,
+					   XLogSegNo nextSegNo, XLogSegNo *curSegNo,
+					   TimeLineID *curSegTimeline)
+{
+	int			pathlen;
+	XLogSegNo	segNo;
+	TimeLineID	timeline;
+	char	   *fname;
+
+	/* We are only interested in normal files. */
+	if (member->is_directory || member->is_link)
+		return false;
+
+	pathlen = strlen(member->pathname);
+	if (pathlen < XLOG_FNAME_LEN)
+		return false;
+
+	/* WAL file could be with full path */
+	fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+	if (!IsXLogFileName(fname))
+		return false;
+
+	/* Parse position from file */
+	XLogFromFileName(fname, &timeline, &segNo, WalSegSz);
+
+	/* Ignore if the timeline is different */
+	if (startTimeLineID != timeline)
+		return false;
+
+	/* Skip if the current segment is not the desired one */
+	if (startSegNo > segNo || endSegNo < segNo)
+		return false;
+
+	*curSegNo = segNo;
+	*curSegTimeline = timeline;
+
+	return true;
+}
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 937e0d68841..2a0300dc339 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -3,6 +3,7 @@
 pg_waldump_sources = files(
   'compat.c',
   'pg_waldump.c',
+  'astreamer_waldump.c',
   'rmgrdesc.c',
 )
 
@@ -18,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, lz4, zstd],
+  dependencies: [frontend_code, lz4, zstd, libpq],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
@@ -29,6 +30,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'TAR': tar.found() ? tar.full_path() : ''},
     'tests': [
       't/001_basic.pl',
       't/002_save_fullpage.pl',
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 8d0cd9e7156..d136f8f038e 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -326,6 +326,160 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/*
+ * Returns true if the given file is a tar archive and outputs its compression
+ * algorithm.
+ */
+static bool
+is_tar_file(const char *fname, pg_compress_algorithm *compression)
+{
+	int			fname_len = strlen(fname);
+	pg_compress_algorithm compress_algo;
+
+	/* Now, check the compression type of the tar */
+	if (fname_len > 4 &&
+		strcmp(fname + fname_len - 4, ".tar") == 0)
+		compress_algo = PG_COMPRESSION_NONE;
+	else if (fname_len > 4 &&
+			 strcmp(fname + fname_len - 4, ".tgz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 7 &&
+			 strcmp(fname + fname_len - 7, ".tar.gz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.lz4") == 0)
+		compress_algo = PG_COMPRESSION_LZ4;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.zst") == 0)
+		compress_algo = PG_COMPRESSION_ZSTD;
+	else
+		return false;
+
+	*compression = compress_algo;
+
+	return true;
+}
+
+/*
+ * Creates an appropriate chain of archive streamers for reading the given
+ * tar archive.
+ */
+static void
+setup_astreamer(XLogDumpPrivate *private, pg_compress_algorithm compression,
+				XLogRecPtr startptr, XLogRecPtr endptr)
+{
+	astreamer  *streamer = NULL;
+
+	streamer = astreamer_waldump_content_new(NULL, startptr, endptr, private);
+
+	/*
+	 * Final extracted WAL data will reside in this streamer. However, since
+	 * it sits at the bottom of the stack and isn't designed to propagate data
+	 * upward, we need to hold a pointer to its data buffer in order to copy.
+	 */
+	private->archive_streamer_buf = &streamer->bbs_buffer;
+
+	/* Before that we must parse the tar archive. */
+	streamer = astreamer_tar_parser_new(streamer);
+
+	/* Before that we must decompress, if archive is compressed. */
+	if (compression == PG_COMPRESSION_GZIP)
+		streamer = astreamer_gzip_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_LZ4)
+		streamer = astreamer_lz4_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_ZSTD)
+		streamer = astreamer_zstd_decompressor_new(streamer);
+
+	private->archive_streamer = streamer;
+}
+
+/*
+ * Initializes the archive reader for a tar file.
+ */
+static void
+init_tar_archive_reader(XLogDumpPrivate *private, char *waldir,
+						pg_compress_algorithm compression)
+{
+	int			fd;
+
+	/* Now, the tar archive and store its file descriptor */
+	fd = open_file_in_directory(waldir, private->archive_name);
+
+	if (fd < 0)
+		pg_fatal("could not open file \"%s\"", private->archive_name);
+
+	private->archive_fd = fd;
+
+	/* Setup tar archive reading facility */
+	setup_astreamer(private, compression, private->startptr, private->endptr);
+}
+
+/*
+ * Release the archive streamer chain and close the archive file.
+ */
+static void
+free_tar_archive_reader(XLogDumpPrivate *private)
+{
+	/*
+	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
+	 * flush any remaining buffered data or to ensure the end of the tar
+	 * archive is reached. However, when decoding a WAL file, once we hit the
+	 * end LSN, any remaining WAL data in the buffer or the tar archive's
+	 * unreached end can be safely ignored.
+	 */
+	astreamer_free(private->archive_streamer);
+
+	/* Close the file. */
+	if (close(private->archive_fd) != 0)
+		pg_log_error("could not close file \"%s\": %m",
+					 private->archive_name);
+}
+
+/*
+ * Reads a WAL page from the archive and verifies WAL segment size.
+ */
+static void
+verify_tar_archive(XLogDumpPrivate *private, const char *waldir,
+				   pg_compress_algorithm compression)
+{
+	PGAlignedXLogBlock buf;
+	int			r;
+
+	setup_astreamer(private, compression, InvalidXLogRecPtr, InvalidXLogRecPtr);
+
+	/* Now, the tar archive and store its file descriptor */
+	private->archive_fd = open_file_in_directory(waldir, private->archive_name);
+
+	if (private->archive_fd < 0)
+		pg_fatal("could not open file \"%s\"", private->archive_name);
+
+	/* Read a wal page */
+	r = astreamer_wal_read(buf.data, InvalidXLogRecPtr, XLOG_BLCKSZ, private);
+
+	/* Set WalSegSz if WAL data is successfully read */
+	if (r == XLOG_BLCKSZ)
+	{
+		XLogLongPageHeader longhdr = (XLogLongPageHeader) buf.data;
+
+		WalSegSz = longhdr->xlp_seg_size;
+
+		if (!IsValidWalSegSize(WalSegSz))
+		{
+			pg_log_error(ngettext("invalid WAL segment size in WAL file \"%s\" (%d byte)",
+								  "invalid WAL segment size in WAL file \"%s\" (%d bytes)",
+								  WalSegSz),
+						 private->archive_name, WalSegSz);
+			pg_log_error_detail("The WAL segment size must be a power of two between 1 MB and 1 GB.");
+			exit(1);
+		}
+	}
+	else
+		pg_fatal("could not read WAL data from \"%s\" archive: read %d of %d",
+				 private->archive_name, r, XLOG_BLCKSZ);
+
+	free_tar_archive_reader(private);
+}
+
 /* Returns the size in bytes of the data to be read. */
 static inline int
 required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
@@ -406,7 +560,7 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = required_read_len(private, targetPagePtr, reqLen);
+	int			count = required_read_len(private, targetPtr, reqLen);
 	WALReadError errinfo;
 
 	if (private->endptr_reached)
@@ -436,6 +590,44 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 	return count;
 }
 
+/*
+ * pg_waldump's XLogReaderRoutine->segment_open callback to support dumping WAL
+ * files from tar archives.
+ */
+static void
+TarWALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
+					  TimeLineID *tli_p)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->segment_close callback.
+ */
+static void
+TarWALDumpCloseSegment(XLogReaderState *state)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->page_read callback to support dumping WAL
+ * files from tar archives.
+ */
+static int
+TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				   XLogRecPtr targetPtr, char *readBuff)
+{
+	XLogDumpPrivate *private = state->private_data;
+	int			count = required_read_len(private, targetPtr, reqLen);
+
+	if (private->endptr_reached)
+		return -1;
+
+	/* Read the WAL page from the archive streamer */
+	return astreamer_wal_read(readBuff, targetPagePtr, count, private);
+}
+
 /*
  * Boolean to return whether the given WAL record matches a specific relation
  * and optionally block.
@@ -773,8 +965,8 @@ usage(void)
 	printf(_("  -F, --fork=FORK        only show records that modify blocks in fork FORK;\n"
 			 "                         valid names are main, fsm, vm, init\n"));
 	printf(_("  -n, --limit=N          number of records to display\n"));
-	printf(_("  -p, --path=PATH        directory in which to find WAL segment files or a\n"
-			 "                         directory with a ./pg_wal that contains such files\n"
+	printf(_("  -p, --path=PATH        tar archive or a directory in which to find WAL segment files or\n"
+			 "                         a directory with a ./pg_wal that contains such files\n"
 			 "                         (default: current directory, ./pg_wal, $PGDATA/pg_wal)\n"));
 	printf(_("  -q, --quiet            do not print any output, except for errors\n"));
 	printf(_("  -r, --rmgr=RMGR        only show records generated by resource manager RMGR;\n"
@@ -806,7 +998,10 @@ main(int argc, char **argv)
 	XLogRecord *record;
 	XLogRecPtr	first_record;
 	char	   *waldir = NULL;
+	char	   *walpath = NULL;
 	char	   *errormsg;
+	bool		is_tar = false;
+	pg_compress_algorithm compression;
 
 	static struct option long_options[] = {
 		{"bkp-details", no_argument, NULL, 'b'},
@@ -938,7 +1133,7 @@ main(int argc, char **argv)
 				}
 				break;
 			case 'p':
-				waldir = pg_strdup(optarg);
+				walpath = pg_strdup(optarg);
 				break;
 			case 'q':
 				config.quiet = true;
@@ -1102,10 +1297,20 @@ main(int argc, char **argv)
 		goto bad_argument;
 	}
 
-	if (waldir != NULL)
+	if (walpath != NULL)
 	{
+		/* validate path points to tar archive */
+		if (is_tar_file(walpath, &compression))
+		{
+			char	   *fname = NULL;
+
+			split_path(walpath, &waldir, &fname);
+
+			private.archive_name = fname;
+			is_tar = true;
+		}
 		/* validate path points to directory */
-		if (!verify_directory(waldir))
+		else if (!verify_directory(walpath))
 		{
 			pg_log_error("could not open directory \"%s\": %m", waldir);
 			goto bad_argument;
@@ -1125,44 +1330,23 @@ main(int argc, char **argv)
 
 		split_path(argv[optind], &directory, &fname);
 
-		if (waldir == NULL && directory != NULL)
+		if (walpath == NULL && directory != NULL)
 		{
-			waldir = directory;
+			walpath = directory;
 
-			if (!verify_directory(waldir))
+			if (!verify_directory(walpath))
 				pg_fatal("could not open directory \"%s\": %m", waldir);
 		}
 
-		waldir = identify_target_directory(waldir, fname);
-		fd = open_file_in_directory(waldir, fname);
-		if (fd < 0)
-			pg_fatal("could not open file \"%s\"", fname);
-		close(fd);
-
-		/* parse position from file */
-		XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
-
-		if (XLogRecPtrIsInvalid(private.startptr))
-			XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
-		else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+		if (fname != NULL && is_tar_file(fname, &compression))
 		{
-			pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.startptr),
-						 fname);
-			goto bad_argument;
+			private.archive_name = fname;
+			waldir = walpath ? pg_strdup(walpath) : pg_strdup(".");
+			is_tar = true;
 		}
-
-		/* no second file specified, set end position */
-		if (!(optind + 1 < argc) && XLogRecPtrIsInvalid(private.endptr))
-			XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
-
-		/* parse ENDSEG if passed */
-		if (optind + 1 < argc)
+		else
 		{
-			XLogSegNo	endsegno;
-
-			/* ignore directory, already have that */
-			split_path(argv[optind + 1], &directory, &fname);
+			waldir = identify_target_directory(walpath, fname);
 
 			fd = open_file_in_directory(waldir, fname);
 			if (fd < 0)
@@ -1170,32 +1354,67 @@ main(int argc, char **argv)
 			close(fd);
 
 			/* parse position from file */
-			XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+			XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
 
-			if (endsegno < segno)
-				pg_fatal("ENDSEG %s is before STARTSEG %s",
-						 argv[optind + 1], argv[optind]);
+			if (XLogRecPtrIsInvalid(private.startptr))
+				XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
+			else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+			{
+				pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.startptr),
+							 fname);
+				goto bad_argument;
+			}
 
-			if (XLogRecPtrIsInvalid(private.endptr))
-				XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
-										private.endptr);
+			/* no second file specified, set end position */
+			if (!(optind + 1 < argc) && XLogRecPtrIsInvalid(private.endptr))
+				XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
 
-			/* set segno to endsegno for check of --end */
-			segno = endsegno;
-		}
+			/* parse ENDSEG if passed */
+			if (optind + 1 < argc)
+			{
+				XLogSegNo	endsegno;
 
+				/* ignore directory, already have that */
+				split_path(argv[optind + 1], &directory, &fname);
 
-		if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
-			private.endptr != (segno + 1) * WalSegSz)
-		{
-			pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.endptr),
-						 argv[argc - 1]);
-			goto bad_argument;
+				fd = open_file_in_directory(waldir, fname);
+				if (fd < 0)
+					pg_fatal("could not open file \"%s\"", fname);
+				close(fd);
+
+				/* parse position from file */
+				XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+
+				if (endsegno < segno)
+					pg_fatal("ENDSEG %s is before STARTSEG %s",
+							 argv[optind + 1], argv[optind]);
+
+				if (XLogRecPtrIsInvalid(private.endptr))
+					XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
+											private.endptr);
+
+				/* set segno to endsegno for check of --end */
+				segno = endsegno;
+			}
+
+
+			if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
+				private.endptr != (segno + 1) * WalSegSz)
+			{
+				pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.endptr),
+							 argv[argc - 1]);
+				goto bad_argument;
+			}
 		}
 	}
-	else
-		waldir = identify_target_directory(waldir, NULL);
+	else if (!is_tar)
+		waldir = identify_target_directory(walpath, NULL);
+
+	/* Verify that the archive contains valid WAL files */
+	if (is_tar)
+		verify_tar_archive(&private, waldir, compression);
 
 	/* we don't know what to print */
 	if (XLogRecPtrIsInvalid(private.startptr))
@@ -1207,12 +1426,30 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
-	xlogreader_state =
-		XLogReaderAllocate(WalSegSz, waldir,
-						   XL_ROUTINE(.page_read = WALDumpReadPage,
-									  .segment_open = WALDumpOpenSegment,
-									  .segment_close = WALDumpCloseSegment),
-						   &private);
+	if (is_tar)
+	{
+		/* Set up for reading tar file */
+		init_tar_archive_reader(&private, waldir, compression);
+
+		/* Routine to decode WAL files in tar archive */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = TarWALDumpReadPage,
+										  .segment_open = TarWALDumpOpenSegment,
+										  .segment_close = TarWALDumpCloseSegment),
+							   &private);
+	}
+	else
+	{
+		/* Routine to decode WAL files */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = WALDumpReadPage,
+										  .segment_open = WALDumpOpenSegment,
+										  .segment_close = WALDumpCloseSegment),
+							   &private);
+	}
+
 	if (!xlogreader_state)
 		pg_fatal("out of memory while allocating a WAL reading processor");
 
@@ -1321,6 +1558,9 @@ main(int argc, char **argv)
 
 	XLogReaderFree(xlogreader_state);
 
+	if (is_tar)
+		free_tar_archive_reader(&private);
+
 	return EXIT_SUCCESS;
 
 bad_argument:
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 9e62b64ead5..b5d440500de 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -12,6 +12,8 @@
 #define PG_WALDUMP_H
 
 #include "access/xlogdefs.h"
+#include "fe_utils/astreamer.h"
+#include "lib/stringinfo.h"
 
 extern int	WalSegSz;
 
@@ -22,6 +24,23 @@ typedef struct XLogDumpPrivate
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	bool		endptr_reached;
+
+	/* Fields required to read WAL from archive */
+	char	   *archive_name;	/* Tar archive name */
+	int			archive_fd;		/* File descriptor for the open tar file */
+
+	astreamer  *archive_streamer;
+	StringInfo	archive_streamer_buf;	/* Buffer for receiving WAL data */
+	XLogRecPtr	archive_streamer_read_ptr; /* Populate the buffer with records
+											  until this record pointer */
 } XLogDumpPrivate;
 
-#endif		/* end of PG_WALDUMP_H */
+
+extern astreamer *astreamer_waldump_content_new(astreamer *next,
+												XLogRecPtr startptr,
+												XLogRecPtr endptr,
+												XLogDumpPrivate *privateInfo);
+extern int	astreamer_wal_read(char *readBuff, XLogRecPtr startptr, Size count,
+							   XLogDumpPrivate *privateInfo);
+
+#endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 1b712e8d74d..443126a9ce6 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -3,10 +3,13 @@
 
 use strict;
 use warnings FATAL => 'all';
+use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
 
+my $tar = $ENV{TAR};
+
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
 program_options_handling_ok('pg_waldump');
@@ -235,7 +238,7 @@ command_like(
 sub test_pg_waldump
 {
 	local $Test::Builder::Level = $Test::Builder::Level + 1;
-	my @opts = @_;
+	my ($path, @opts) = @_;
 
 	my ($stdout, $stderr);
 
@@ -243,6 +246,7 @@ sub test_pg_waldump
 		'pg_waldump',
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
+		'--path' => $path,
 		@opts
 	  ],
 	  '>' => \$stdout,
@@ -254,11 +258,50 @@ sub test_pg_waldump
 	return @lines;
 }
 
-my @lines;
+# Create a tar archive, sorting the file order
+sub generate_archive
+{
+	my ($archive, $directory, $compression_flags) = @_;
+
+	my @files;
+	opendir my $dh, $directory or die "opendir: $!";
+	while (my $entry = readdir $dh) {
+		# Skip '.' and '..'
+		next if $entry eq '.' || $entry eq '..';
+		push @files, $entry;
+	}
+	closedir $dh;
+
+	@files = sort @files;
+
+	# move into the WAL directory before archiving files
+	my $cwd = getcwd;
+	chdir($directory) || die "chdir: $!";
+	command_ok([$tar, $compression_flags, $archive, @files]);
+	chdir($cwd) || die "chdir: $!";
+}
+
+my $tmp_dir = PostgreSQL::Test::Utils::tempdir_short();
 
 my @scenario = (
 	{
-		'path' => $node->data_dir
+		'path' => $node->data_dir,
+		'is_archive' => 0,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar",
+		'compression_method' => 'none',
+		'compression_flags' => '-cf',
+		'is_archive' => 1,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar.gz",
+		'compression_method' => 'gzip',
+		'compression_flags' => '-czf',
+		'is_archive' => 1,
+		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
 	});
 
 for my $scenario (@scenario)
@@ -267,6 +310,19 @@ for my $scenario (@scenario)
 
 	SKIP:
 	{
+		skip "tar command is not available", 3
+		  if !defined $tar;
+		skip "$scenario->{'compression_method'} compression not supported by this build", 3
+		  if !$scenario->{'enabled'} && $scenario->{'is_archive'};
+
+		  # create pg_wal archive
+		  if ($scenario->{'is_archive'})
+		  {
+			  generate_archive($path,
+				  $node->data_dir . '/pg_wal',
+				  $scenario->{'compression_flags'});
+		  }
+
 		command_fails_like(
 			[ 'pg_waldump', '--path' => $path ],
 			qr/error: no start WAL location given/,
@@ -298,38 +354,42 @@ for my $scenario (@scenario)
 			qr/error: error in WAL record at/,
 			'errors are shown with --quiet');
 
-		@lines = test_pg_waldump('--path' => $path);
+		my @lines;
+		@lines = test_pg_waldump($path);
 		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		@lines = test_pg_waldump($path, '--limit' => 6);
 		is(@lines, 6, 'limit option observed');
 
-		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		@lines = test_pg_waldump($path, '--fullpage');
 		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats');
+		@lines = test_pg_waldump($path, '--stats');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		@lines = test_pg_waldump($path, '--stats=record');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		@lines = test_pg_waldump($path, '--rmgr' => 'Btree');
 		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		@lines = test_pg_waldump($path, '--fork' => 'init');
 		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
 		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
 			0, 'only lines for selected relation');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
 			'--block' => 1);
 		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+
+		# Cleanup.
+		unlink $path if $scenario->{'is_archive'};
 	}
 }
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index a13e8162890..b406ca041ec 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -3444,6 +3444,7 @@ astreamer_recovery_injector
 astreamer_tar_archiver
 astreamer_tar_parser
 astreamer_verify
+astreamer_waldump
 astreamer_zstd_frame
 auth_password_hook_typ
 autovac_table
-- 
2.47.1

From cf0201067a8627049838e85eecbe5da9aa9c8ef0 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Mon, 25 Aug 2025 17:26:29 +0530
Subject: [PATCH v3 5/8] pg_waldump: Remove the restriction on the order of
 archived WAL files.

With previous patch, pg_waldump would stop decoding if WAL files were
not in the required sequence. With this patch, decoding will now
continue.  Any WAL file that is out of order will be written to a
temporary location, from which it will be read later. Once a temporary
file has been read, it will be removed.
---
 doc/src/sgml/ref/pg_waldump.sgml       |   7 +-
 src/bin/pg_waldump/astreamer_waldump.c | 189 +++++++++++++++++++++----
 src/bin/pg_waldump/pg_waldump.c        |  75 +++++++++-
 src/bin/pg_waldump/pg_waldump.h        |  26 +++-
 src/bin/pg_waldump/t/001_basic.pl      |   3 +-
 5 files changed, 266 insertions(+), 34 deletions(-)

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index d004bb0f67e..c1afb4097b5 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -149,8 +149,11 @@ PostgreSQL documentation
         of <envar>PGDATA</envar>.
        </para>
        <para>
-        If a tar archive is provided, its WAL segment files must be in
-        sequential order; otherwise, an error will be reported.
+        If a tar archive is provided and its WAL segment files are not in
+        sequential order, those files will be written temporarily. These files
+        will be created inside the directory specified by the <envar>TMPDIR</envar>
+        environment variable if it is set; otherwise, the temporary files will
+        be created within the same directory as the tar archive itself.
        </para>
       </listitem>
      </varlistentry>
diff --git a/src/bin/pg_waldump/astreamer_waldump.c b/src/bin/pg_waldump/astreamer_waldump.c
index 61876e834a9..183f389d3f1 100644
--- a/src/bin/pg_waldump/astreamer_waldump.c
+++ b/src/bin/pg_waldump/astreamer_waldump.c
@@ -18,8 +18,8 @@
 
 #include "access/xlog_internal.h"
 #include "access/xlogdefs.h"
+#include "common/file_perm.h"
 #include "common/logging.h"
-#include "fe_utils/simple_list.h"
 #include "pg_waldump.h"
 
 /*
@@ -37,6 +37,8 @@ typedef struct astreamer_waldump
 
 	/* These fields change with archive member. */
 	bool		skipThisSeg;
+	bool		writeThisSeg;
+	FILE	   *segFp;
 	XLogSegNo	nextSegNo;		/* Next expected segment to stream */
 } astreamer_waldump;
 
@@ -53,8 +55,15 @@ static bool member_is_relevant_wal(astreamer_member *member,
 								   XLogSegNo startSegNo,
 								   XLogSegNo endSegNo,
 								   XLogSegNo nextSegNo,
+								   char **curFname,
 								   XLogSegNo *curSegNo,
 								   TimeLineID *curSegTimeline);
+static FILE *member_prepare_tmp_write(XLogSegNo curSegNo,
+									  const char *fname,
+									  XLogDumpPrivate *privateInfo);
+static XLogSegNo member_next_segno(XLogSegNo curSegNo,
+								   TimeLineID timeline,
+								   XLogDumpPrivate *privateInfo);
 
 static const astreamer_ops astreamer_waldump_ops = {
 	.content = astreamer_waldump_content,
@@ -189,17 +198,8 @@ astreamer_waldump_content_new(astreamer *next, XLogRecPtr startptr,
 	if (XLogRecPtrIsInvalid(startptr))
 		streamer->startSegNo = 0;
 	else
-	{
 		XLByteToSeg(startptr, streamer->startSegNo, WalSegSz);
 
-		/*
-		 * Initialize the record pointer to the beginning of the first
-		 * segment; this pointer will track the WAL record reading status.
-		 */
-		XLogSegNoOffsetToRecPtr(streamer->startSegNo, 0, WalSegSz,
-								privateInfo->archive_streamer_read_ptr);
-	}
-
 	if (XLogRecPtrIsInvalid(endPtr))
 		streamer->endSegNo = UINT64_MAX;
 	else
@@ -228,19 +228,21 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 	{
 		case ASTREAMER_MEMBER_HEADER:
 			{
+				char	   *fname;
 				XLogSegNo	segNo;
 				TimeLineID	timeline;
 
 				pg_log_debug("pg_waldump: reading \"%s\"", member->pathname);
 
 				mystreamer->skipThisSeg = false;
+				mystreamer->writeThisSeg = false;
 
 				if (!member_is_relevant_wal(member,
 											privateInfo->timeline,
 											mystreamer->startSegNo,
 											mystreamer->endSegNo,
 											mystreamer->nextSegNo,
-											&segNo, &timeline))
+											&fname, &segNo, &timeline))
 				{
 					mystreamer->skipThisSeg = true;
 					break;
@@ -254,24 +256,38 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 				if (mystreamer->nextSegNo == 0)
 					break;
 
-				/* WAL segments must be archived in order */
+				/*
+				 * When WAL segments are not archived sequentially, it becomes
+				 * necessary to write out (or preserve) segments that might be
+				 * required at a later point.
+				 */
 				if (mystreamer->nextSegNo != segNo)
 				{
-					pg_log_error("WAL files are not archived in sequential order");
-					pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
-										mystreamer->nextSegNo, segNo);
-					exit(1);
+					mystreamer->writeThisSeg = true;
+					mystreamer->segFp =
+						member_prepare_tmp_write(segNo, fname, privateInfo);
+					break;
 				}
 
 				/*
-				 * We track the reading of WAL segment records using a pointer
-				 * that's continuously incremented by the length of the
-				 * received data. This pointer is crucial for serving WAL page
-				 * requests from the WAL decoding routine, so it must be
-				 * accurate.
+				 * We are now streaming segment containt.
+				 *
+				 * We need to track the reading of WAL segment records using a
+				 * pointer that's typically incremented by the length of the
+				 * data read. However, we sometimes export the WAL file to
+				 * temporary storage, allowing the decoding routine to read
+				 * directly from there. This makes continuous pointer
+				 * incrementing challenging, as file reads can occur from any
+				 * offset, leading to potential errors. Therefore, we now
+				 * reset the pointer when reading from a file for streaming.
+				 * Also, if there's any existing data in the buffer, the next
+				 * WAL record should logically follow it.
 				 */
 #ifdef USE_ASSERT_CHECKING
-				if (mystreamer->nextSegNo != 0)
+				Assert(!mystreamer->skipThisSeg);
+				Assert(!mystreamer->writeThisSeg);
+
+				if (privateInfo->archive_streamer_buf->len != 0)
 				{
 					XLogRecPtr	recPtr;
 
@@ -280,11 +296,19 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 				}
 #endif
 
+				/*
+				 * Initialized to the beginning of the current segment being
+				 * streamed through the buffer.
+				 */
+				XLogSegNoOffsetToRecPtr(segNo, 0, WalSegSz,
+										privateInfo->archive_streamer_read_ptr);
+
 				/* Save the timeline */
 				privateInfo->timeline = timeline;
 
 				/* Update the next expected segment number */
-				mystreamer->nextSegNo += 1;
+				mystreamer->nextSegNo =
+					member_next_segno(segNo, timeline, privateInfo);
 			}
 			break;
 
@@ -293,12 +317,44 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 			if (mystreamer->skipThisSeg)
 				break;
 
+			/* Or, write contents to file */
+			if (mystreamer->writeThisSeg)
+			{
+				Assert(mystreamer->segFp != NULL);
+
+				errno = 0;
+				if (len > 0 && fwrite(data, len, 1, mystreamer->segFp) != 1)
+				{
+					char	   *fname;
+					int			pathlen = strlen(member->pathname);
+
+					Assert(pathlen >= XLOG_FNAME_LEN);
+
+					fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+
+					/*
+					 * If write didn't set errno, assume problem is no disk
+					 * space
+					 */
+					if (errno == 0)
+						errno = ENOSPC;
+					pg_fatal("could not write to file \"%s/%s\": %m",
+							 privateInfo->tmpdir, fname);
+				}
+				break;
+			}
+
 			/* Or, copy contents to buffer */
 			privateInfo->archive_streamer_read_ptr += len;
 			astreamer_buffer_bytes(streamer, &data, &len, len);
 			break;
 
 		case ASTREAMER_MEMBER_TRAILER:
+			if (mystreamer->segFp != NULL)
+			{
+				fclose(mystreamer->segFp);
+				mystreamer->segFp = NULL;
+			}
 			break;
 
 		case ASTREAMER_ARCHIVE_TRAILER:
@@ -325,8 +381,14 @@ astreamer_waldump_finalize(astreamer *streamer)
 static void
 astreamer_waldump_free(astreamer *streamer)
 {
+	astreamer_waldump *mystreamer;
+
 	Assert(streamer->bbs_next == NULL);
 
+	mystreamer = (astreamer_waldump *) streamer;
+	if (mystreamer->segFp != NULL)
+		fclose(mystreamer->segFp);
+
 	pfree(streamer->bbs_buffer.data);
 	pfree(streamer);
 }
@@ -339,8 +401,8 @@ astreamer_waldump_free(astreamer *streamer)
 static bool
 member_is_relevant_wal(astreamer_member *member, TimeLineID startTimeLineID,
 					   XLogSegNo startSegNo, XLogSegNo endSegNo,
-					   XLogSegNo nextSegNo, XLogSegNo *curSegNo,
-					   TimeLineID *curSegTimeline)
+					   XLogSegNo nextSegNo, char **curFname,
+					   XLogSegNo *curSegNo, TimeLineID *curSegTimeline)
 {
 	int			pathlen;
 	XLogSegNo	segNo;
@@ -371,8 +433,85 @@ member_is_relevant_wal(astreamer_member *member, TimeLineID startTimeLineID,
 	if (startSegNo > segNo || endSegNo < segNo)
 		return false;
 
+	*curFname = fname;
 	*curSegNo = segNo;
 	*curSegTimeline = timeline;
 
 	return true;
 }
+
+/*
+ * Create an empty placeholder file and return its handle.  The file is also
+ * added to an exported list for future management, e.g.  access, deletion, and
+ * existence checks.
+ */
+static FILE *
+member_prepare_tmp_write(XLogSegNo curSegNo, const char *fname,
+						 XLogDumpPrivate *privateInfo)
+{
+	FILE	   *file;
+	char	   *fpath = get_tmp_wal_file_path(privateInfo, fname);
+
+	/* Create an empty placeholder */
+	file = fopen(fpath, PG_BINARY_W);
+	if (file == NULL)
+		pg_fatal("could not create file \"%s\": %m", fpath);
+
+#ifndef WIN32
+	if (chmod(fpath, pg_file_create_mode))
+		pg_fatal("could not set permissions on file \"%s\": %m",
+				 fpath);
+#endif
+
+	/* Record this segment's export */
+	simple_string_list_append(&privateInfo->exportedSegList, fname);
+	pfree(fpath);
+
+	return file;
+}
+
+/*
+ * Get next WAL segment that needs to be retrieved from the archive.
+ *
+ * The function checks for the presence of a previously read and extracted WAL
+ * segment in the temporary storage. If a temporary file is found for that
+ * segment, it indicates the segment has already been successfully retrieved
+ * from the archive. In this case, the function increments the segment number
+ * and repeats the check. This process continues until a segment that has not
+ * yet been retrieved is found, at which point the function returns its number.
+ */
+static XLogSegNo
+member_next_segno(XLogSegNo curSegNo, TimeLineID timeline,
+				  XLogDumpPrivate *privateInfo)
+{
+	XLogSegNo	nextSegNo = curSegNo + 1;
+	bool		exists;
+
+	/*
+	 * If we find a file that was previously written to the temporary space,
+	 * it indicates that the corresponding WAL segment request has already
+	 * been fulfilled. In that case, we increment the nextSegNo counter and
+	 * check again whether that segment number again. if found above steps
+	 * will be return if not then we return that segment number which would be
+	 * needed from the archive.
+	 */
+	do
+	{
+		char		fname[MAXFNAMELEN];
+
+		XLogFileName(fname, timeline, nextSegNo, WalSegSz);
+
+		/*
+		 * If the WAL segment has already been exported, increment the counter
+		 * and check for the next segment.
+		 */
+		exists = false;
+		if (simple_string_list_member(&privateInfo->exportedSegList, fname))
+		{
+			nextSegNo += 1;
+			exists = true;
+		}
+	} while (exists);
+
+	return nextSegNo;
+}
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index d136f8f038e..d57458d3148 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -394,13 +394,14 @@ setup_astreamer(XLogDumpPrivate *private, pg_compress_algorithm compression,
 }
 
 /*
- * Initializes the archive reader for a tar file.
+ * Initializes the tar archive reader and a temporary directory for WAL files.
  */
 static void
 init_tar_archive_reader(XLogDumpPrivate *private, char *waldir,
 						pg_compress_algorithm compression)
 {
 	int			fd;
+	char	   *tmpdir;
 
 	/* Now, the tar archive and store its file descriptor */
 	fd = open_file_in_directory(waldir, private->archive_name);
@@ -412,6 +413,15 @@ init_tar_archive_reader(XLogDumpPrivate *private, char *waldir,
 
 	/* Setup tar archive reading facility */
 	setup_astreamer(private, compression, private->startptr, private->endptr);
+
+	/* Temporary space for writing WAL segments */
+	if (getenv("TMPDIR"))
+		tmpdir = pg_strdup(getenv("TMPDIR"));
+	else
+		tmpdir = waldir != NULL ? pg_strdup(waldir) : pg_strdup(".");
+	canonicalize_path(tmpdir);
+
+	private->tmpdir = tmpdir;
 }
 
 /*
@@ -420,6 +430,8 @@ init_tar_archive_reader(XLogDumpPrivate *private, char *waldir,
 static void
 free_tar_archive_reader(XLogDumpPrivate *private)
 {
+	SimpleStringListCell *cell;
+
 	/*
 	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
 	 * flush any remaining buffered data or to ensure the end of the tar
@@ -433,6 +445,15 @@ free_tar_archive_reader(XLogDumpPrivate *private)
 	if (close(private->archive_fd) != 0)
 		pg_log_error("could not close file \"%s\": %m",
 					 private->archive_name);
+
+	/* Clear out any existing temporary files */
+	for (cell = private->exportedSegList.head; cell; cell = cell->next)
+	{
+		char	   *fpath = get_tmp_wal_file_path(private, cell->val);
+
+		unlink(fpath);
+		pfree(fpath);
+	}
 }
 
 /*
@@ -560,7 +581,7 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = required_read_len(private, targetPtr, reqLen);
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
 	if (private->endptr_reached)
@@ -619,12 +640,58 @@ TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				   XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = required_read_len(private, targetPtr, reqLen);
+	int			count = required_read_len(private, targetPagePtr, reqLen);
+	XLogSegNo	nextSegNo;
 
 	if (private->endptr_reached)
 		return -1;
 
-	/* Read the WAL page from the archive streamer */
+	/*
+	 * If the target page is in a different segment, first check for the WAL
+	 * segment's physical existence in the temporary directory.
+	 */
+	nextSegNo = state->seg.ws_segno;
+	if (!XLByteInSeg(targetPagePtr, nextSegNo, WalSegSz))
+	{
+		char		fname[MAXPGPATH];
+		char	   *fpath;
+
+		if (state->seg.ws_file >= 0)
+		{
+			close(state->seg.ws_file);
+			state->seg.ws_file = -1;
+
+			/* Remove this file, as it is no longer needed. */
+			XLogFileName(fname, state->seg.ws_tli, nextSegNo, WalSegSz);
+			fpath = get_tmp_wal_file_path(private, fname);
+			unlink(fpath);
+			pfree(fpath);
+		}
+
+		XLByteToSeg(targetPagePtr, nextSegNo, WalSegSz);
+		state->seg.ws_tli = private->timeline;
+		state->seg.ws_segno = nextSegNo;
+
+		/*
+		 * If the next segment exists, open it and continue reading from there
+		 */
+		XLogFileName(fname, private->timeline, nextSegNo, WalSegSz);
+		if (simple_string_list_member(&private->exportedSegList, fname))
+		{
+			fpath = get_tmp_wal_file_path(private, fname);
+			state->seg.ws_file = open(fpath, O_RDONLY | PG_BINARY, 0);
+
+			if (state->seg.ws_file < 0)
+				pg_fatal("could not open file \"%s\": %m", fpath);
+		}
+	}
+
+	/* Continue reading from the open WAL segment, if any */
+	if (state->seg.ws_file >= 0)
+		return WALDumpReadPage(state, targetPagePtr, reqLen, targetPtr,
+							   readBuff);
+
+	/* Otherwise, read the WAL page from the archive streamer */
 	return astreamer_wal_read(readBuff, targetPagePtr, count, private);
 }
 
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index b5d440500de..614e679cb96 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -13,8 +13,11 @@
 
 #include "access/xlogdefs.h"
 #include "fe_utils/astreamer.h"
+#include "fe_utils/simple_list.h"
 #include "lib/stringinfo.h"
 
+#define TEMP_FILE_EXT	"waldump.tmp"
+
 extern int	WalSegSz;
 
 /* Contains the necessary information to drive WAL decoding */
@@ -31,11 +34,30 @@ typedef struct XLogDumpPrivate
 
 	astreamer  *archive_streamer;
 	StringInfo	archive_streamer_buf;	/* Buffer for receiving WAL data */
-	XLogRecPtr	archive_streamer_read_ptr; /* Populate the buffer with records
-											  until this record pointer */
+	XLogRecPtr	archive_streamer_read_ptr;	/* Populate the buffer with
+											 * records until this record
+											 * pointer */
+	char	   *tmpdir;			/* Temporary direcotry to export file */
+	SimpleStringList exportedSegList;	/* Temporary exported WAL file list */
 } XLogDumpPrivate;
 
 
+/*
+ * Generate the temporary WAL file path.
+ *
+ * Note that the caller is responsible to pfree it.
+ */
+static inline char *
+get_tmp_wal_file_path(XLogDumpPrivate *privateInfo, const char *fname)
+{
+	char	   *fpath = (char *) palloc(MAXPGPATH);
+
+	snprintf(fpath, MAXPGPATH, "%s/%s.%s", privateInfo->tmpdir, fname,
+			 TEMP_FILE_EXT);
+
+	return fpath;
+}
+
 extern astreamer *astreamer_waldump_content_new(astreamer *next,
 												XLogRecPtr startptr,
 												XLogRecPtr endptr,
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 443126a9ce6..d5fa1f6d28d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -7,6 +7,7 @@ use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
+use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
 
@@ -272,7 +273,7 @@ sub generate_archive
 	}
 	closedir $dh;
 
-	@files = sort @files;
+	@files = shuffle @files;
 
 	# move into the WAL directory before archiving files
 	my $cwd = getcwd;
-- 
2.47.1

From 60c2ecfbe80203c73fb35d763eb63a9fad7fff45 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 14:47:43 +0530
Subject: [PATCH v3 6/8] pg_verifybackup: Delay default WAL directory
 preparation.

We are not sure whether to parse WAL from a directory or an archive
until the backup format is known. Therefore, we delay preparing the
default WAL directory until the point of parsing. This delay is
harmless, as the WAL directory is not used elsewhere.
---
 src/bin/pg_verifybackup/pg_verifybackup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 5e6c13bb921..31ebc1581fb 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -285,10 +285,6 @@ main(int argc, char **argv)
 		manifest_path = psprintf("%s/backup_manifest",
 								 context.backup_directory);
 
-	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
-
 	/*
 	 * Try to read the manifest. We treat any errors encountered while parsing
 	 * the manifest as fatal; there doesn't seem to be much point in trying to
@@ -368,6 +364,10 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
+	/* By default, look for the WAL in the backup directory, too. */
+	if (wal_directory == NULL)
+		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
-- 
2.47.1

From 18ce61a331aa5800cd3e42b13faaa3e9b39fdc7e Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 24 Jul 2025 16:37:43 +0530
Subject: [PATCH v3 7/8] pg_verifybackup: Rename the wal-directory switch to
 wal-path

Future patches to pg_waldump will enable it to decode WAL directly
from tar files. This means you'll be able to specify a tar archive
path instead of a traditional WAL directory.

To keep things consistent and more versatile, we should also
generalize the input switch for pg_verifybackup. It should accept
either a directory or a tar file path that contains WALs. This change
will also aligning it with the existing manifest-path switch naming.
---
 doc/src/sgml/ref/pg_verifybackup.sgml     |  2 +-
 src/bin/pg_verifybackup/pg_verifybackup.c | 22 +++++++++++-----------
 src/bin/pg_verifybackup/po/de.po          |  4 ++--
 src/bin/pg_verifybackup/po/el.po          |  4 ++--
 src/bin/pg_verifybackup/po/es.po          |  4 ++--
 src/bin/pg_verifybackup/po/fr.po          |  4 ++--
 src/bin/pg_verifybackup/po/it.po          |  4 ++--
 src/bin/pg_verifybackup/po/ja.po          |  4 ++--
 src/bin/pg_verifybackup/po/ka.po          |  4 ++--
 src/bin/pg_verifybackup/po/ko.po          |  4 ++--
 src/bin/pg_verifybackup/po/ru.po          |  4 ++--
 src/bin/pg_verifybackup/po/sv.po          |  4 ++--
 src/bin/pg_verifybackup/po/uk.po          |  4 ++--
 src/bin/pg_verifybackup/po/zh_CN.po       |  4 ++--
 src/bin/pg_verifybackup/po/zh_TW.po       |  4 ++--
 src/bin/pg_verifybackup/t/007_wal.pl      |  4 ++--
 16 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index 61c12975e4a..e9b8bfd51b1 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -261,7 +261,7 @@ PostgreSQL documentation
 
      <varlistentry>
       <term><option>-w <replaceable class="parameter">path</replaceable></option></term>
-      <term><option>--wal-directory=<replaceable class="parameter">path</replaceable></option></term>
+      <term><option>--wal-path=<replaceable class="parameter">path</replaceable></option></term>
       <listitem>
        <para>
         Try to parse WAL files stored in the specified directory, rather than
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 31ebc1581fb..1ee400199da 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -93,7 +93,7 @@ static void verify_file_checksum(verifier_context *context,
 								 uint8 *buffer);
 static void parse_required_wal(verifier_context *context,
 							   char *pg_waldump_path,
-							   char *wal_directory);
+							   char *wal_path);
 static astreamer *create_archive_verifier(verifier_context *context,
 										  char *archive_name,
 										  Oid tblspc_oid,
@@ -126,7 +126,7 @@ main(int argc, char **argv)
 		{"progress", no_argument, NULL, 'P'},
 		{"quiet", no_argument, NULL, 'q'},
 		{"skip-checksums", no_argument, NULL, 's'},
-		{"wal-directory", required_argument, NULL, 'w'},
+		{"wal-path", required_argument, NULL, 'w'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -135,7 +135,7 @@ main(int argc, char **argv)
 	char	   *manifest_path = NULL;
 	bool		no_parse_wal = false;
 	bool		quiet = false;
-	char	   *wal_directory = NULL;
+	char	   *wal_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -221,8 +221,8 @@ main(int argc, char **argv)
 				context.skip_checksums = true;
 				break;
 			case 'w':
-				wal_directory = pstrdup(optarg);
-				canonicalize_path(wal_directory);
+				wal_path = pstrdup(optarg);
+				canonicalize_path(wal_path);
 				break;
 			default:
 				/* getopt_long already emitted a complaint */
@@ -365,15 +365,15 @@ main(int argc, char **argv)
 		verify_backup_checksums(&context);
 
 	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+	if (wal_path == NULL)
+		wal_path = psprintf("%s/pg_wal", context.backup_directory);
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
 	 */
 	if (!no_parse_wal)
-		parse_required_wal(&context, pg_waldump_path, wal_directory);
+		parse_required_wal(&context, pg_waldump_path, wal_path);
 
 	/*
 	 * If everything looks OK, tell the user this, unless we were asked to
@@ -1198,7 +1198,7 @@ verify_file_checksum(verifier_context *context, manifest_file *m,
  */
 static void
 parse_required_wal(verifier_context *context, char *pg_waldump_path,
-				   char *wal_directory)
+				   char *wal_path)
 {
 	manifest_data *manifest = context->manifest;
 	manifest_wal_range *this_wal_range = manifest->first_wal_range;
@@ -1208,7 +1208,7 @@ parse_required_wal(verifier_context *context, char *pg_waldump_path,
 		char	   *pg_waldump_cmd;
 
 		pg_waldump_cmd = psprintf("\"%s\" --quiet --path=\"%s\" --timeline=%u --start=%X/%08X --end=%X/%08X\n",
-								  pg_waldump_path, wal_directory, this_wal_range->tli,
+								  pg_waldump_path, wal_path, this_wal_range->tli,
 								  LSN_FORMAT_ARGS(this_wal_range->start_lsn),
 								  LSN_FORMAT_ARGS(this_wal_range->end_lsn));
 		fflush(NULL);
@@ -1376,7 +1376,7 @@ usage(void)
 	printf(_("  -P, --progress              show progress information\n"));
 	printf(_("  -q, --quiet                 do not print any output, except for errors\n"));
 	printf(_("  -s, --skip-checksums        skip checksum verification\n"));
-	printf(_("  -w, --wal-directory=PATH    use specified path for WAL files\n"));
+	printf(_("  -w, --wal-path=PATH         use specified path for WAL files\n"));
 	printf(_("  -V, --version               output version information, then exit\n"));
 	printf(_("  -?, --help                  show this help, then exit\n"));
 	printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
diff --git a/src/bin/pg_verifybackup/po/de.po b/src/bin/pg_verifybackup/po/de.po
index a9e24931100..9b5cd5898cf 100644
--- a/src/bin/pg_verifybackup/po/de.po
+++ b/src/bin/pg_verifybackup/po/de.po
@@ -785,8 +785,8 @@ msgstr "  -s, --skip-checksums        Überprüfung der Prüfsummen überspringe
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/el.po b/src/bin/pg_verifybackup/po/el.po
index 3e3f20c67c5..81442f51c17 100644
--- a/src/bin/pg_verifybackup/po/el.po
+++ b/src/bin/pg_verifybackup/po/el.po
@@ -494,8 +494,8 @@ msgstr "  -s, --skip-checksums        παράκαμψε την επαλήθευ
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/es.po b/src/bin/pg_verifybackup/po/es.po
index 0cb958f3448..7f729fa35ba 100644
--- a/src/bin/pg_verifybackup/po/es.po
+++ b/src/bin/pg_verifybackup/po/es.po
@@ -495,8 +495,8 @@ msgstr "  -s, --skip-checksums        omitir la verificación de la suma de comp
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    utilizar la ruta especificada para los archivos WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    utilizar la ruta especificada para los archivos WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/fr.po b/src/bin/pg_verifybackup/po/fr.po
index da8c72f6427..09937966fa7 100644
--- a/src/bin/pg_verifybackup/po/fr.po
+++ b/src/bin/pg_verifybackup/po/fr.po
@@ -498,8 +498,8 @@ msgstr "  -s, --skip-checksums        ignore la vérification des sommes de cont
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/it.po b/src/bin/pg_verifybackup/po/it.po
index 317b0b71e7f..4da68d0074e 100644
--- a/src/bin/pg_verifybackup/po/it.po
+++ b/src/bin/pg_verifybackup/po/it.po
@@ -472,8 +472,8 @@ msgstr "  -s, --skip-checksums         salta la verifica del checksum\n"
 
 #: pg_verifybackup.c:911
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH     usa il percorso specificato per i file WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH     usa il percorso specificato per i file WAL\n"
 
 #: pg_verifybackup.c:912
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ja.po b/src/bin/pg_verifybackup/po/ja.po
index c910fb236cc..a948959b54f 100644
--- a/src/bin/pg_verifybackup/po/ja.po
+++ b/src/bin/pg_verifybackup/po/ja.po
@@ -672,8 +672,8 @@ msgstr "  -s, --skip-checksums        チェックサム検証をスキップ\n"
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    WALファイルに指定したパスを使用する\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    WALファイルに指定したパスを使用する\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ka.po b/src/bin/pg_verifybackup/po/ka.po
index 982751984c7..ef2799316a8 100644
--- a/src/bin/pg_verifybackup/po/ka.po
+++ b/src/bin/pg_verifybackup/po/ka.po
@@ -784,8 +784,8 @@ msgstr "  -s, --skip-checksums        საკონტროლო ჯამ
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ko.po b/src/bin/pg_verifybackup/po/ko.po
index acdc3da5e02..eaf91ef1e98 100644
--- a/src/bin/pg_verifybackup/po/ko.po
+++ b/src/bin/pg_verifybackup/po/ko.po
@@ -501,8 +501,8 @@ msgstr "  -s, --skip-checksums        체크섬 검사 건너뜀\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=경로    WAL 파일이 있는 경로 지정\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=경로    WAL 파일이 있는 경로 지정\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ru.po b/src/bin/pg_verifybackup/po/ru.po
index 64005feedfd..7fb0e5ab1f6 100644
--- a/src/bin/pg_verifybackup/po/ru.po
+++ b/src/bin/pg_verifybackup/po/ru.po
@@ -507,9 +507,9 @@ msgstr "  -s, --skip-checksums        пропустить проверку ко
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
 msgstr ""
-"  -w, --wal-directory=ПУТЬ    использовать заданный путь к файлам WAL\n"
+"  -w, --wal-path=ПУТЬ    использовать заданный путь к файлам WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/sv.po b/src/bin/pg_verifybackup/po/sv.po
index 17240feeb5c..97125838e8c 100644
--- a/src/bin/pg_verifybackup/po/sv.po
+++ b/src/bin/pg_verifybackup/po/sv.po
@@ -492,8 +492,8 @@ msgstr "  -s, --skip-checksums        hoppa över verifiering av kontrollsummor\
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=SÖKVÄG  använd denna sökväg till WAL-filer\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=SÖKVÄG  använd denna sökväg till WAL-filer\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/uk.po b/src/bin/pg_verifybackup/po/uk.po
index 034b9764232..63f8041ab38 100644
--- a/src/bin/pg_verifybackup/po/uk.po
+++ b/src/bin/pg_verifybackup/po/uk.po
@@ -484,8 +484,8 @@ msgstr "  -s, --skip-checksums не перевіряти контрольні с
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH використовувати вказаний шлях для файлів WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH використовувати вказаний шлях для файлів WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_CN.po b/src/bin/pg_verifybackup/po/zh_CN.po
index b7d97c8976d..fb6fcae8b82 100644
--- a/src/bin/pg_verifybackup/po/zh_CN.po
+++ b/src/bin/pg_verifybackup/po/zh_CN.po
@@ -465,8 +465,8 @@ msgstr "  -s, --skip-checksums        跳过校验和验证\n"
 
 #: pg_verifybackup.c:919
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    对WAL文件使用指定路径\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    对WAL文件使用指定路径\n"
 
 #: pg_verifybackup.c:920
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_TW.po b/src/bin/pg_verifybackup/po/zh_TW.po
index c1b710b0a36..568f972b0bb 100644
--- a/src/bin/pg_verifybackup/po/zh_TW.po
+++ b/src/bin/pg_verifybackup/po/zh_TW.po
@@ -555,8 +555,8 @@ msgstr "  -s, --skip-checksums        跳過檢查碼驗證\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    用指定的路徑存放 WAL 檔\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    用指定的路徑存放 WAL 檔\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/t/007_wal.pl b/src/bin/pg_verifybackup/t/007_wal.pl
index babc4f0a86b..b07f80719b0 100644
--- a/src/bin/pg_verifybackup/t/007_wal.pl
+++ b/src/bin/pg_verifybackup/t/007_wal.pl
@@ -42,10 +42,10 @@ command_ok([ 'pg_verifybackup', '--no-parse-wal', $backup_path ],
 command_ok(
 	[
 		'pg_verifybackup',
-		'--wal-directory' => $relocated_pg_wal,
+		'--wal-path' => $relocated_pg_wal,
 		$backup_path
 	],
-	'--wal-directory can be used to specify WAL directory');
+	'--wal-path can be used to specify WAL directory');
 
 # Move directory back to original location.
 rename($relocated_pg_wal, $original_pg_wal) || die "rename pg_wal back: $!";
-- 
2.47.1

From b3bd75e44fa50c89b52f650d4978fcb69d768652 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 17 Jul 2025 16:39:36 +0530
Subject: [PATCH v3 8/8] pg_verifybackup: enabled WAL parsing for tar-format
 backup

Now that pg_waldump supports decoding from tar archives, we should
leverage this functionality to remove the previous restriction on WAL
parsing for tar-backed formats.
---
 doc/src/sgml/ref/pg_verifybackup.sgml         |  5 +-
 src/bin/pg_verifybackup/pg_verifybackup.c     | 66 +++++++++++++------
 src/bin/pg_verifybackup/t/002_algorithm.pl    |  4 --
 src/bin/pg_verifybackup/t/003_corruption.pl   |  4 +-
 src/bin/pg_verifybackup/t/008_untar.pl        |  3 +-
 src/bin/pg_verifybackup/t/010_client_untar.pl |  3 +-
 6 files changed, 50 insertions(+), 35 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index e9b8bfd51b1..16b50b5a4df 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -36,10 +36,7 @@ PostgreSQL documentation
    <literal>backup_manifest</literal> generated by the server at the time
    of the backup. The backup may be stored either in the "plain" or the "tar"
    format; this includes tar-format backups compressed with any algorithm
-   supported by <application>pg_basebackup</application>. However, at present,
-   <literal>WAL</literal> verification is supported only for plain-format
-   backups. Therefore, if the backup is stored in tar-format, the
-   <literal>-n, --no-parse-wal</literal> option should be used.
+   supported by <application>pg_basebackup</application>.
   </para>
 
   <para>
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 1ee400199da..4bfe6fdff16 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -74,7 +74,9 @@ pg_noreturn static void report_manifest_error(JsonManifestParseContext *context,
 											  const char *fmt,...)
 			pg_attribute_printf(2, 3);
 
-static void verify_tar_backup(verifier_context *context, DIR *dir);
+static void verify_tar_backup(verifier_context *context, DIR *dir,
+							  char **base_archive_path,
+							  char **wal_archive_path);
 static void verify_plain_backup_directory(verifier_context *context,
 										  char *relpath, char *fullpath,
 										  DIR *dir);
@@ -83,7 +85,9 @@ static void verify_plain_backup_file(verifier_context *context, char *relpath,
 static void verify_control_file(const char *controlpath,
 								uint64 manifest_system_identifier);
 static void precheck_tar_backup_file(verifier_context *context, char *relpath,
-									 char *fullpath, SimplePtrList *tarfiles);
+									 char *fullpath, SimplePtrList *tarfiles,
+									 char **base_archive_path,
+									 char **wal_archive_path);
 static void verify_tar_file(verifier_context *context, char *relpath,
 							char *fullpath, astreamer *streamer);
 static void report_extra_backup_files(verifier_context *context);
@@ -136,6 +140,8 @@ main(int argc, char **argv)
 	bool		no_parse_wal = false;
 	bool		quiet = false;
 	char	   *wal_path = NULL;
+	char	   *base_archive_path = NULL;
+	char	   *wal_archive_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -327,17 +333,6 @@ main(int argc, char **argv)
 		pfree(path);
 	}
 
-	/*
-	 * XXX: In the future, we should consider enhancing pg_waldump to read WAL
-	 * files from an archive.
-	 */
-	if (!no_parse_wal && context.format == 't')
-	{
-		pg_log_error("pg_waldump cannot read tar files");
-		pg_log_error_hint("You must use -n/--no-parse-wal when verifying a tar-format backup.");
-		exit(1);
-	}
-
 	/*
 	 * Perform the appropriate type of verification appropriate based on the
 	 * backup format. This will close 'dir'.
@@ -346,7 +341,7 @@ main(int argc, char **argv)
 		verify_plain_backup_directory(&context, NULL, context.backup_directory,
 									  dir);
 	else
-		verify_tar_backup(&context, dir);
+		verify_tar_backup(&context, dir, &base_archive_path, &wal_archive_path);
 
 	/*
 	 * The "matched" flag should now be set on every entry in the hash table.
@@ -364,9 +359,28 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
-	/* By default, look for the WAL in the backup directory, too. */
+	/*
+	 * By default, WAL files are expected to be found in the backup directory
+	 * for plain-format backups. In the case of tar-format backups, if a
+	 * separate WAL archive is not found, the WAL files are most likely
+	 * included within the main data directory archive.
+	 */
 	if (wal_path == NULL)
-		wal_path = psprintf("%s/pg_wal", context.backup_directory);
+	{
+		if (context.format == 'p')
+			wal_path = psprintf("%s/pg_wal", context.backup_directory);
+		else if (wal_archive_path)
+			wal_path = wal_archive_path;
+		else if (base_archive_path)
+			wal_path = base_archive_path;
+		else
+		{
+			pg_log_error("wal archive not found");
+			pg_log_error_hint("Specify the correct path using the option -w/--wal-path."
+							  "Or you must use -n/--no-parse-wal when verifying a tar-format backup.");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
@@ -787,7 +801,8 @@ verify_control_file(const char *controlpath, uint64 manifest_system_identifier)
  * close when we're done with it.
  */
 static void
-verify_tar_backup(verifier_context *context, DIR *dir)
+verify_tar_backup(verifier_context *context, DIR *dir, char **base_archive_path,
+				  char **wal_archive_path)
 {
 	struct dirent *dirent;
 	SimplePtrList tarfiles = {NULL, NULL};
@@ -816,7 +831,8 @@ verify_tar_backup(verifier_context *context, DIR *dir)
 			char	   *fullpath;
 
 			fullpath = psprintf("%s/%s", context->backup_directory, filename);
-			precheck_tar_backup_file(context, filename, fullpath, &tarfiles);
+			precheck_tar_backup_file(context, filename, fullpath, &tarfiles,
+									 base_archive_path, wal_archive_path);
 			pfree(fullpath);
 		}
 	}
@@ -875,11 +891,13 @@ verify_tar_backup(verifier_context *context, DIR *dir)
  *
  * The arguments to this function are mostly the same as the
  * verify_plain_backup_file. The additional argument outputs a list of valid
- * tar files.
+ * tar files, along with the full paths to the main archive and the WAL
+ * directory archive.
  */
 static void
 precheck_tar_backup_file(verifier_context *context, char *relpath,
-						 char *fullpath, SimplePtrList *tarfiles)
+						 char *fullpath, SimplePtrList *tarfiles,
+						 char **base_archive_path, char **wal_archive_path)
 {
 	struct stat sb;
 	Oid			tblspc_oid = InvalidOid;
@@ -918,9 +936,17 @@ precheck_tar_backup_file(verifier_context *context, char *relpath,
 	 * extension such as .gz, .lz4, or .zst.
 	 */
 	if (strncmp("base", relpath, 4) == 0)
+	{
 		suffix = relpath + 4;
+
+		*base_archive_path = pstrdup(fullpath);
+	}
 	else if (strncmp("pg_wal", relpath, 6) == 0)
+	{
 		suffix = relpath + 6;
+
+		*wal_archive_path = pstrdup(fullpath);
+	}
 	else
 	{
 		/* Expected a <tablespaceoid>.tar file here. */
diff --git a/src/bin/pg_verifybackup/t/002_algorithm.pl b/src/bin/pg_verifybackup/t/002_algorithm.pl
index ae16c11bc4d..4f284a9e828 100644
--- a/src/bin/pg_verifybackup/t/002_algorithm.pl
+++ b/src/bin/pg_verifybackup/t/002_algorithm.pl
@@ -30,10 +30,6 @@ sub test_checksums
 	{
 		# Add switch to get a tar-format backup
 		push @backup, ('--format' => 'tar');
-
-		# Add switch to skip WAL verification, which is not yet supported for
-		# tar-format backups
-		push @verify, ('--no-parse-wal');
 	}
 
 	# A backup with a bogus algorithm should fail.
diff --git a/src/bin/pg_verifybackup/t/003_corruption.pl b/src/bin/pg_verifybackup/t/003_corruption.pl
index 1dd60f709cf..f1ebdbb46b4 100644
--- a/src/bin/pg_verifybackup/t/003_corruption.pl
+++ b/src/bin/pg_verifybackup/t/003_corruption.pl
@@ -193,10 +193,8 @@ for my $scenario (@scenario)
 			command_ok([ $tar, '-cf' => "$tar_backup_path/base.tar", '.' ]);
 			chdir($cwd) || die "chdir: $!";
 
-			# Now check that the backup no longer verifies. We must use -n
-			# here, because pg_waldump can't yet read WAL from a tarfile.
 			command_fails_like(
-				[ 'pg_verifybackup', '--no-parse-wal', $tar_backup_path ],
+				[ 'pg_verifybackup', $tar_backup_path ],
 				$scenario->{'fails_like'},
 				"corrupt backup fails verification: $name");
 
diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index bc3d6b352ad..0cfe1f9532c 100644
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -123,8 +123,7 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index b62faeb5acf..76269a73673 100644
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -137,8 +137,7 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
-- 
2.47.1

From 8eb84b553d856bbbffda254e419152c236346848 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 24 Jun 2025 11:33:20 +0530
Subject: [PATCH v4 1/8] Refactor: pg_waldump: Move some declarations to new
 pg_waldump.h

This change prepares for a second source file in this directory to
support reading WAL from tar files. Common structures, declarations,
and functions are being exported through this include file so
they can be used in both files.
---
 src/bin/pg_waldump/pg_waldump.c | 11 ++---------
 src/bin/pg_waldump/pg_waldump.h | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 9 deletions(-)
 create mode 100644 src/bin/pg_waldump/pg_waldump.h

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 13d3ec2f5be..a49b2fd96c7 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -29,6 +29,7 @@
 #include "common/logging.h"
 #include "common/relpath.h"
 #include "getopt_long.h"
+#include "pg_waldump.h"
 #include "rmgrdesc.h"
 #include "storage/bufpage.h"
 
@@ -39,19 +40,11 @@
 
 static const char *progname;
 
-static int	WalSegSz;
+int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 static volatile sig_atomic_t time_to_stop = false;
 
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
-typedef struct XLogDumpPrivate
-{
-	TimeLineID	timeline;
-	XLogRecPtr	startptr;
-	XLogRecPtr	endptr;
-	bool		endptr_reached;
-} XLogDumpPrivate;
-
 typedef struct XLogDumpConfig
 {
 	/* display options */
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
new file mode 100644
index 00000000000..9e62b64ead5
--- /dev/null
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -0,0 +1,27 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_waldump.h - decode and display WAL
+ *
+ * Copyright (c) 2013-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  src/bin/pg_waldump/pg_waldump.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_WALDUMP_H
+#define PG_WALDUMP_H
+
+#include "access/xlogdefs.h"
+
+extern int	WalSegSz;
+
+/* Contains the necessary information to drive WAL decoding */
+typedef struct XLogDumpPrivate
+{
+	TimeLineID	timeline;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
+	bool		endptr_reached;
+} XLogDumpPrivate;
+
+#endif		/* end of PG_WALDUMP_H */
-- 
2.47.1

From 9f719d5744c293a91aca5a933b357296180281ff Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 26 Jun 2025 11:42:53 +0530
Subject: [PATCH v4 2/8] Refactor: pg_waldump: Separate logic used to calculate
 the required read size.

This refactoring prepares the codebase for an upcoming patch that will
support reading WAL from tar files. The logic for calculating the
required read size has been updated to handle both normal WAL files
and WAL files located inside a tar archive.
---
 src/bin/pg_waldump/pg_waldump.c | 39 ++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index a49b2fd96c7..8d0cd9e7156 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -326,6 +326,29 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/* Returns the size in bytes of the data to be read. */
+static inline int
+required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
+				  int reqLen)
+{
+	int			count = XLOG_BLCKSZ;
+
+	if (private->endptr != InvalidXLogRecPtr)
+	{
+		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
+			count = XLOG_BLCKSZ;
+		else if (targetPagePtr + reqLen <= private->endptr)
+			count = private->endptr - targetPagePtr;
+		else
+		{
+			private->endptr_reached = true;
+			return -1;
+		}
+	}
+
+	return count;
+}
+
 /* pg_waldump's XLogReaderRoutine->segment_open callback */
 static void
 WALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
@@ -383,21 +406,11 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = XLOG_BLCKSZ;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
-	if (private->endptr != InvalidXLogRecPtr)
-	{
-		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
-			count = XLOG_BLCKSZ;
-		else if (targetPagePtr + reqLen <= private->endptr)
-			count = private->endptr - targetPagePtr;
-		else
-		{
-			private->endptr_reached = true;
-			return -1;
-		}
-	}
+	if (private->endptr_reached)
+		return -1;
 
 	if (!WALRead(state, readBuff, targetPagePtr, count, private->timeline,
 				 &errinfo))
-- 
2.47.1

From f51ddb6d02ef6e3383beebdd4486d10191499955 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 30 Jul 2025 12:43:30 +0530
Subject: [PATCH v4 3/8] Refactor: pg_waldump: Restructure TAP tests.

Restructured some tests to run inside a loop, facilitating their
re-execution for decoding WAL from tar archives.
---
 src/bin/pg_waldump/t/001_basic.pl | 123 ++++++++++++++++--------------
 1 file changed, 67 insertions(+), 56 deletions(-)

diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index f26d75e01cf..1b712e8d74d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -198,28 +198,6 @@ command_like(
 	],
 	qr/./,
 	'runs with start and end segment specified');
-command_fails_like(
-	[ 'pg_waldump', '--path' => $node->data_dir ],
-	qr/error: no start WAL location given/,
-	'path option requires start location');
-command_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-		'--end' => $end_lsn,
-	],
-	qr/./,
-	'runs with path option and start and end locations');
-command_fails_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-	],
-	qr/error: error in WAL record at/,
-	'falling off the end of the WAL results in an error');
-
 command_like(
 	[
 		'pg_waldump', '--quiet',
@@ -227,15 +205,6 @@ command_like(
 	],
 	qr/^$/,
 	'no output with --quiet option');
-command_fails_like(
-	[
-		'pg_waldump', '--quiet',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn
-	],
-	qr/error: error in WAL record at/,
-	'errors are shown with --quiet');
-
 
 # Test for: Display a message that we're skipping data if `from`
 # wasn't a pointer to the start of a record.
@@ -272,7 +241,6 @@ sub test_pg_waldump
 
 	my $result = IPC::Run::run [
 		'pg_waldump',
-		'--path' => $node->data_dir,
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
 		@opts
@@ -288,38 +256,81 @@ sub test_pg_waldump
 
 my @lines;
 
-@lines = test_pg_waldump;
-is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
+my @scenario = (
+	{
+		'path' => $node->data_dir
+	});
 
-@lines = test_pg_waldump('--limit' => 6);
-is(@lines, 6, 'limit option observed');
+for my $scenario (@scenario)
+{
+	my $path = $scenario->{'path'};
 
-@lines = test_pg_waldump('--fullpage');
-is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
+	SKIP:
+	{
+		command_fails_like(
+			[ 'pg_waldump', '--path' => $path ],
+			qr/error: no start WAL location given/,
+			'path option requires start location');
+		command_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+				'--end' => $end_lsn,
+			],
+			qr/./,
+			'runs with path option and start and end locations');
+		command_fails_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+			],
+			qr/error: error in WAL record at/,
+			'falling off the end of the WAL results in an error');
 
-@lines = test_pg_waldump('--stats');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		command_fails_like(
+			[
+				'pg_waldump', '--quiet',
+				'--path' => $path,
+				'--start' => $start_lsn
+			],
+			qr/error: error in WAL record at/,
+			'errors are shown with --quiet');
 
-@lines = test_pg_waldump('--stats=record');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		@lines = test_pg_waldump('--path' => $path);
+		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-@lines = test_pg_waldump('--rmgr' => 'Btree');
-is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		is(@lines, 6, 'limit option observed');
 
-@lines = test_pg_waldump('--fork' => 'init');
-is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
-is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
-	0, 'only lines for selected relation');
+		@lines = test_pg_waldump('--path' => $path, '--stats');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
-	'--block' => 1);
-is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
+		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+
+		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
+		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
+			0, 'only lines for selected relation');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
+			'--block' => 1);
+		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+	}
+}
 
 done_testing();
-- 
2.47.1

From be0cf9b0d4ff99630298e499f93d09a17eeae141 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 18:37:59 +0530
Subject: [PATCH v4 4/8] pg_waldump: Add support for archived WAL decoding.

pg_waldump can now accept the path to a tar archive containing WAL
files and decode them. This feature was added primarily for
pg_verifybackup, which previously disabled WAL parsing for
tar-formatted backups.

Note that this patch requires that the WAL files within the archive be
in sequential order; an error will be reported otherwise. The next
patch is planned to remove this restriction.
---
 doc/src/sgml/ref/pg_waldump.sgml       |   8 +-
 src/bin/pg_waldump/Makefile            |   7 +-
 src/bin/pg_waldump/astreamer_waldump.c | 388 +++++++++++++++++++++++++
 src/bin/pg_waldump/meson.build         |   4 +-
 src/bin/pg_waldump/pg_waldump.c        | 365 +++++++++++++++++++----
 src/bin/pg_waldump/pg_waldump.h        |  20 +-
 src/bin/pg_waldump/t/001_basic.pl      |  84 +++++-
 src/tools/pgindent/typedefs.list       |   1 +
 8 files changed, 799 insertions(+), 78 deletions(-)
 create mode 100644 src/bin/pg_waldump/astreamer_waldump.c

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index ce23add5577..d004bb0f67e 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -141,13 +141,17 @@ PostgreSQL documentation
       <term><option>--path=<replaceable>path</replaceable></option></term>
       <listitem>
        <para>
-        Specifies a directory to search for WAL segment files or a
-        directory with a <literal>pg_wal</literal> subdirectory that
+        Specifies a tar archive or a directory to search for WAL segment files
+        or a directory with a <literal>pg_wal</literal> subdirectory that
         contains such files.  The default is to search in the current
         directory, the <literal>pg_wal</literal> subdirectory of the
         current directory, and the <literal>pg_wal</literal> subdirectory
         of <envar>PGDATA</envar>.
        </para>
+       <para>
+        If a tar archive is provided, its WAL segment files must be in
+        sequential order; otherwise, an error will be reported.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index 4c1ee649501..b234613eb50 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -3,6 +3,9 @@
 PGFILEDESC = "pg_waldump - decode and display WAL"
 PGAPPICON=win32
 
+# make these available to TAP test scripts
+export TAR
+
 subdir = src/bin/pg_waldump
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
@@ -12,11 +15,13 @@ OBJS = \
 	$(WIN32RES) \
 	compat.o \
 	pg_waldump.o \
+	astreamer_waldump.o \
 	rmgrdesc.o \
 	xlogreader.o \
 	xlogstats.o
 
-override CPPFLAGS := -DFRONTEND $(CPPFLAGS)
+override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
diff --git a/src/bin/pg_waldump/astreamer_waldump.c b/src/bin/pg_waldump/astreamer_waldump.c
new file mode 100644
index 00000000000..caf7da6ccb8
--- /dev/null
+++ b/src/bin/pg_waldump/astreamer_waldump.c
@@ -0,0 +1,388 @@
+/*-------------------------------------------------------------------------
+ *
+ * astreamer_waldump.c
+ *		A generic facility for reading WAL data from tar archives via archive
+ *		streamer.
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/bin/pg_waldump/astreamer_waldump.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <unistd.h>
+
+#include "access/xlog_internal.h"
+#include "access/xlogdefs.h"
+#include "common/logging.h"
+#include "fe_utils/simple_list.h"
+#include "pg_waldump.h"
+
+/*
+ * How many bytes should we try to read from a file at once?
+ */
+#define READ_CHUNK_SIZE				(128 * 1024)
+
+/*
+ * When nextSegNo is 0, read from any available WAL file.
+ */
+#define READ_ANY_WAL(mystreamer)	((mystreamer)->nextSegNo == 0)
+
+typedef struct astreamer_waldump
+{
+	/* These fields don't change once initialized. */
+	astreamer	base;
+	XLogSegNo	startSegNo;
+	XLogSegNo	endSegNo;
+	XLogDumpPrivate *privateInfo;
+
+	/* These fields change with archive member. */
+	bool		skipThisSeg;
+	XLogSegNo	nextSegNo;		/* Next expected segment to stream */
+} astreamer_waldump;
+
+static int	astreamer_archive_read(XLogDumpPrivate *privateInfo);
+static void astreamer_waldump_content(astreamer *streamer,
+									  astreamer_member *member,
+									  const char *data, int len,
+									  astreamer_archive_context context);
+static void astreamer_waldump_finalize(astreamer *streamer);
+static void astreamer_waldump_free(astreamer *streamer);
+
+static bool member_is_relevant_wal(astreamer_waldump *mystreamer,
+								   astreamer_member *member,
+								   TimeLineID startTimeLineID,
+								   XLogSegNo *curSegNo);
+
+static const astreamer_ops astreamer_waldump_ops = {
+	.content = astreamer_waldump_content,
+	.finalize = astreamer_waldump_finalize,
+	.free = astreamer_waldump_free
+};
+
+/*
+ * Copies WAL data from astreamer to readBuff; if unavailable, fetches more
+ * from the tar archive via astreamer.
+ */
+int
+astreamer_wal_read(char *readBuff, XLogRecPtr targetPagePtr, Size count,
+				   XLogDumpPrivate *privateInfo)
+{
+	char	   *p = readBuff;
+	Size		nbytes = count;
+	XLogRecPtr	recptr = targetPagePtr;
+	volatile StringInfo astreamer_buf = privateInfo->archive_streamer_buf;
+
+	while (nbytes > 0)
+	{
+		char	   *buf = astreamer_buf->data;
+		int			len = astreamer_buf->len;
+
+		/* WAL record range that the buffer contains */
+		XLogRecPtr	endPtr = privateInfo->archive_streamer_read_ptr;
+		XLogRecPtr	startPtr = (endPtr > len) ? endPtr - len : 0;
+
+		/*
+		 * pg_waldump never ask the same WAL bytes more than once, so if we're
+		 * now being asked for data beyond the end of what we've already read,
+		 * that means none of the data we currently have in the buffer will
+		 * ever be consulted again. So, we can discard the existing buffer
+		 * contents and start over.
+		 */
+		if (recptr >= endPtr)
+		{
+			len = 0;
+
+			/* Discard the buffered data */
+			resetStringInfo(astreamer_buf);
+		}
+
+		if (len > 0 && recptr > startPtr)
+		{
+			int			skipBytes = 0;
+
+			/*
+			 * The required offset is not at the start of the archive streamer
+			 * buffer, so skip bytes until reaching the desired offset of the
+			 * target page.
+			 */
+			skipBytes = recptr - startPtr;
+
+			buf += skipBytes;
+			len -= skipBytes;
+		}
+
+		if (len > 0)
+		{
+			int			readBytes = len >= nbytes ? nbytes : len;
+
+			/*
+			 * Ensure we are reading the correct page, unless we've received
+			 * an invalid record pointer. In that specific case, it's
+			 * acceptable to read any page.
+			 */
+			Assert(XLogRecPtrIsInvalid(recptr) ||
+				   (recptr >= startPtr && recptr < endPtr));
+
+			memcpy(p, buf, readBytes);
+
+			/* Update state for read */
+			nbytes -= readBytes;
+			p += readBytes;
+			recptr += readBytes;
+		}
+		else
+		{
+			/* Fetch more data */
+			if (astreamer_archive_read(privateInfo) == 0)
+			{
+				char		fname[MAXFNAMELEN];
+				XLogSegNo	segno;
+
+				XLByteToSeg(targetPagePtr, segno, WalSegSz);
+				XLogFileName(fname, privateInfo->timeline, segno, WalSegSz);
+
+				pg_fatal("could not find file \"%s\" in \"%s\" archive",
+						 fname, privateInfo->archive_name);
+			}
+		}
+	}
+
+	/*
+	 * Should have either have successfully read all the requested bytes or
+	 * reported a failure before this point.
+	 */
+	Assert(nbytes == 0);
+
+	return count;
+}
+
+/*
+ * Reads the archive and passes it to the archive streamer for decompression.
+ */
+static int
+astreamer_archive_read(XLogDumpPrivate *privateInfo)
+{
+	int			rc;
+	char	   *buffer;
+
+	buffer = pg_malloc(READ_CHUNK_SIZE * sizeof(uint8));
+
+	/* Read more data from the tar file */
+	rc = read(privateInfo->archive_fd, buffer, READ_CHUNK_SIZE);
+	if (rc < 0)
+		pg_fatal("could not read file \"%s\": %m",
+				 privateInfo->archive_name);
+
+	/*
+	 * Decrypt (if required), and then parse the previously read contents of
+	 * the tar file.
+	 */
+	if (rc > 0)
+		astreamer_content(privateInfo->archive_streamer, NULL,
+						  buffer, rc, ASTREAMER_UNKNOWN);
+	pg_free(buffer);
+
+	return rc;
+}
+
+/*
+ * Create an astreamer that can read WAL from tar file.
+ */
+astreamer *
+astreamer_waldump_new(XLogRecPtr startptr, XLogRecPtr endPtr,
+					  XLogDumpPrivate *privateInfo)
+{
+	astreamer_waldump *streamer;
+
+	streamer = palloc0(sizeof(astreamer_waldump));
+	*((const astreamer_ops **) &streamer->base.bbs_ops) =
+		&astreamer_waldump_ops;
+
+	initStringInfo(&streamer->base.bbs_buffer);
+
+	if (XLogRecPtrIsInvalid(startptr))
+		streamer->startSegNo = 0;
+	else
+	{
+		XLByteToSeg(startptr, streamer->startSegNo, WalSegSz);
+
+		/*
+		 * Initialize the record pointer to the beginning of the first
+		 * segment; this pointer will track the WAL record reading status.
+		 */
+		XLogSegNoOffsetToRecPtr(streamer->startSegNo, 0, WalSegSz,
+								privateInfo->archive_streamer_read_ptr);
+	}
+
+	if (XLogRecPtrIsInvalid(endPtr))
+		streamer->endSegNo = UINT64_MAX;
+	else
+		XLByteToSeg(endPtr, streamer->endSegNo, WalSegSz);
+
+	streamer->nextSegNo = streamer->startSegNo;
+	streamer->privateInfo = privateInfo;
+
+	return &streamer->base;
+}
+
+/*
+ * Main entry point of the archive streamer for reading WAL from a tar file.
+ */
+static void
+astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
+						  const char *data, int len,
+						  astreamer_archive_context context)
+{
+	astreamer_waldump *mystreamer = (astreamer_waldump *) streamer;
+	XLogDumpPrivate *privateInfo = mystreamer->privateInfo;
+
+	Assert(context != ASTREAMER_UNKNOWN);
+
+	switch (context)
+	{
+		case ASTREAMER_MEMBER_HEADER:
+			{
+				XLogSegNo	segNo;
+
+				pg_log_debug("pg_waldump: reading \"%s\"", member->pathname);
+
+				mystreamer->skipThisSeg = false;
+
+				if (!member_is_relevant_wal(mystreamer, member,
+											privateInfo->timeline, &segNo))
+				{
+					mystreamer->skipThisSeg = true;
+					break;
+				}
+
+				/*
+				 * Further checks are skipped if any WAL file can be read.
+				 * This typically occurs during initial verification.
+				 */
+				if (READ_ANY_WAL(mystreamer))
+					break;
+
+				/* WAL segments must be archived in order */
+				if (mystreamer->nextSegNo != segNo)
+				{
+					pg_log_error("WAL files are not archived in sequential order");
+					pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
+										mystreamer->nextSegNo, segNo);
+					exit(1);
+				}
+
+				/*
+				 * We track the reading of WAL segment records using a pointer
+				 * that's continuously incremented by the length of the
+				 * received data. This pointer is crucial for serving WAL page
+				 * requests from the WAL decoding routine, so it must be
+				 * accurate.
+				 */
+#ifdef USE_ASSERT_CHECKING
+				if (mystreamer->nextSegNo != 0)
+				{
+					XLogRecPtr	recPtr;
+
+					XLogSegNoOffsetToRecPtr(segNo, 0, WalSegSz, recPtr);
+					Assert(privateInfo->archive_streamer_read_ptr == recPtr);
+				}
+#endif
+				/* Update the next expected segment number */
+				mystreamer->nextSegNo += 1;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_CONTENTS:
+			/* Skip this segment */
+			if (mystreamer->skipThisSeg)
+				break;
+
+			/* Or, copy contents to buffer */
+			privateInfo->archive_streamer_read_ptr += len;
+			astreamer_buffer_bytes(streamer, &data, &len, len);
+			break;
+
+		case ASTREAMER_MEMBER_TRAILER:
+			break;
+
+		case ASTREAMER_ARCHIVE_TRAILER:
+			break;
+
+		default:
+			/* Shouldn't happen. */
+			pg_fatal("unexpected state while parsing tar file");
+	}
+}
+
+/*
+ * End-of-stream processing for a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_finalize(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+}
+
+/*
+ * Free memory associated with a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_free(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+
+	pfree(streamer->bbs_buffer.data);
+	pfree(streamer);
+}
+
+/*
+ * Returns true if the archive member name matches the WAL naming format and
+ * the corresponding WAL segment falls within the WAL decoding target range;
+ * otherwise, returns false.
+ */
+static bool
+member_is_relevant_wal(astreamer_waldump *mystreamer, astreamer_member *member,
+					   TimeLineID startTimeLineID, XLogSegNo *curSegNo)
+{
+	int			pathlen;
+	XLogSegNo	segNo;
+	TimeLineID	timeline;
+	char	   *fname;
+
+	/* We are only interested in normal files. */
+	if (member->is_directory || member->is_link)
+		return false;
+
+	pathlen = strlen(member->pathname);
+	if (pathlen < XLOG_FNAME_LEN)
+		return false;
+
+	/* WAL file could be with full path */
+	fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+	if (!IsXLogFileName(fname))
+		return false;
+
+	/* Parse position from file */
+	XLogFromFileName(fname, &timeline, &segNo, WalSegSz);
+
+	/* No further checks are needed if any file ask to read */
+	if (!READ_ANY_WAL(mystreamer))
+	{
+		/* Ignore if the timeline is different */
+		if (startTimeLineID != timeline)
+			return false;
+
+		/* Skip if the current segment is not the desired one */
+		if (mystreamer->startSegNo > segNo || mystreamer->endSegNo < segNo)
+			return false;
+	}
+
+	*curSegNo = segNo;
+
+	return true;
+}
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 937e0d68841..2a0300dc339 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -3,6 +3,7 @@
 pg_waldump_sources = files(
   'compat.c',
   'pg_waldump.c',
+  'astreamer_waldump.c',
   'rmgrdesc.c',
 )
 
@@ -18,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, lz4, zstd],
+  dependencies: [frontend_code, lz4, zstd, libpq],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
@@ -29,6 +30,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'TAR': tar.found() ? tar.full_path() : ''},
     'tests': [
       't/001_basic.pl',
       't/002_save_fullpage.pl',
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 8d0cd9e7156..393d6bfa9ef 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -326,6 +326,148 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/*
+ * Returns true if the given file is a tar archive and outputs its compression
+ * algorithm.
+ */
+static bool
+is_tar_file(const char *fname, pg_compress_algorithm *compression)
+{
+	int			fname_len = strlen(fname);
+	pg_compress_algorithm compress_algo;
+
+	/* Now, check the compression type of the tar */
+	if (fname_len > 4 &&
+		strcmp(fname + fname_len - 4, ".tar") == 0)
+		compress_algo = PG_COMPRESSION_NONE;
+	else if (fname_len > 4 &&
+			 strcmp(fname + fname_len - 4, ".tgz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 7 &&
+			 strcmp(fname + fname_len - 7, ".tar.gz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.lz4") == 0)
+		compress_algo = PG_COMPRESSION_LZ4;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.zst") == 0)
+		compress_algo = PG_COMPRESSION_ZSTD;
+	else
+		return false;
+
+	*compression = compress_algo;
+
+	return true;
+}
+
+/*
+ * Initializes the tar archive reader and a temporary directory for WAL files.
+ */
+static void
+init_tar_archive_reader(XLogDumpPrivate *private, const char *waldir,
+						XLogRecPtr startptr, XLogRecPtr endptr,
+						pg_compress_algorithm compression)
+{
+	int			fd;
+	astreamer  *streamer;
+
+	/* Open tar archive and store its file descriptor */
+	fd = open_file_in_directory(waldir, private->archive_name);
+
+	if (fd < 0)
+		pg_fatal("could not open file \"%s\"", private->archive_name);
+
+	private->archive_fd = fd;
+
+	/*
+	 * Create an appropriate chain of archive streamers for reading the given
+	 * tar archive.
+	 */
+	streamer = astreamer_waldump_new(startptr, endptr, private);
+
+	/*
+	 * Final extracted WAL data will reside in this streamer. However, since
+	 * it sits at the bottom of the stack and isn't designed to propagate data
+	 * upward, we need to hold a pointer to its data buffer in order to copy.
+	 */
+	private->archive_streamer_buf = &streamer->bbs_buffer;
+
+	/* Before that we must parse the tar archive. */
+	streamer = astreamer_tar_parser_new(streamer);
+
+	/* Before that we must decompress, if archive is compressed. */
+	if (compression == PG_COMPRESSION_GZIP)
+		streamer = astreamer_gzip_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_LZ4)
+		streamer = astreamer_lz4_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_ZSTD)
+		streamer = astreamer_zstd_decompressor_new(streamer);
+
+	private->archive_streamer = streamer;
+}
+
+/*
+ * Release the archive streamer chain and close the archive file.
+ */
+static void
+free_tar_archive_reader(XLogDumpPrivate *private)
+{
+	/*
+	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
+	 * flush any remaining buffered data or to ensure the end of the tar
+	 * archive is reached. However, when decoding a WAL file, once we hit the
+	 * end LSN, any remaining WAL data in the buffer or the tar archive's
+	 * unreached end can be safely ignored.
+	 */
+	astreamer_free(private->archive_streamer);
+
+	/* Close the file. */
+	if (close(private->archive_fd) != 0)
+		pg_log_error("could not close file \"%s\": %m",
+					 private->archive_name);
+}
+
+/*
+ * Reads a WAL page from the archive and verifies WAL segment size.
+ */
+static void
+verify_tar_archive(XLogDumpPrivate *private, const char *waldir,
+				   pg_compress_algorithm compression)
+{
+	PGAlignedXLogBlock buf;
+	int			r;
+
+	/* Initialize the reader to stream WAL data from a tar file */
+	init_tar_archive_reader(private, waldir, InvalidXLogRecPtr,
+							InvalidXLogRecPtr, compression);
+
+	/* Read a wal page */
+	r = astreamer_wal_read(buf.data, InvalidXLogRecPtr, XLOG_BLCKSZ, private);
+
+	/* Set WalSegSz if WAL data is successfully read */
+	if (r == XLOG_BLCKSZ)
+	{
+		XLogLongPageHeader longhdr = (XLogLongPageHeader) buf.data;
+
+		WalSegSz = longhdr->xlp_seg_size;
+
+		if (!IsValidWalSegSize(WalSegSz))
+		{
+			pg_log_error(ngettext("invalid WAL segment size in WAL file \"%s\" (%d byte)",
+								  "invalid WAL segment size in WAL file \"%s\" (%d bytes)",
+								  WalSegSz),
+						 private->archive_name, WalSegSz);
+			pg_log_error_detail("The WAL segment size must be a power of two between 1 MB and 1 GB.");
+			exit(1);
+		}
+	}
+	else
+		pg_fatal("could not read WAL data from \"%s\" archive: read %d of %d",
+				 private->archive_name, r, XLOG_BLCKSZ);
+
+	free_tar_archive_reader(private);
+}
+
 /* Returns the size in bytes of the data to be read. */
 static inline int
 required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
@@ -406,7 +548,7 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = required_read_len(private, targetPagePtr, reqLen);
+	int			count = required_read_len(private, targetPtr, reqLen);
 	WALReadError errinfo;
 
 	if (private->endptr_reached)
@@ -436,6 +578,44 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 	return count;
 }
 
+/*
+ * pg_waldump's XLogReaderRoutine->segment_open callback to support dumping WAL
+ * files from tar archives.
+ */
+static void
+TarWALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
+					  TimeLineID *tli_p)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->segment_close callback.
+ */
+static void
+TarWALDumpCloseSegment(XLogReaderState *state)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->page_read callback to support dumping WAL
+ * files from tar archives.
+ */
+static int
+TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				   XLogRecPtr targetPtr, char *readBuff)
+{
+	XLogDumpPrivate *private = state->private_data;
+	int			count = required_read_len(private, targetPtr, reqLen);
+
+	if (private->endptr_reached)
+		return -1;
+
+	/* Read the WAL page from the archive streamer */
+	return astreamer_wal_read(readBuff, targetPagePtr, count, private);
+}
+
 /*
  * Boolean to return whether the given WAL record matches a specific relation
  * and optionally block.
@@ -773,8 +953,8 @@ usage(void)
 	printf(_("  -F, --fork=FORK        only show records that modify blocks in fork FORK;\n"
 			 "                         valid names are main, fsm, vm, init\n"));
 	printf(_("  -n, --limit=N          number of records to display\n"));
-	printf(_("  -p, --path=PATH        directory in which to find WAL segment files or a\n"
-			 "                         directory with a ./pg_wal that contains such files\n"
+	printf(_("  -p, --path=PATH        tar archive or a directory in which to find WAL segment files or\n"
+			 "                         a directory with a ./pg_wal that contains such files\n"
 			 "                         (default: current directory, ./pg_wal, $PGDATA/pg_wal)\n"));
 	printf(_("  -q, --quiet            do not print any output, except for errors\n"));
 	printf(_("  -r, --rmgr=RMGR        only show records generated by resource manager RMGR;\n"
@@ -806,7 +986,10 @@ main(int argc, char **argv)
 	XLogRecord *record;
 	XLogRecPtr	first_record;
 	char	   *waldir = NULL;
+	char	   *walpath = NULL;
 	char	   *errormsg;
+	bool		is_tar = false;
+	pg_compress_algorithm compression;
 
 	static struct option long_options[] = {
 		{"bkp-details", no_argument, NULL, 'b'},
@@ -938,7 +1121,7 @@ main(int argc, char **argv)
 				}
 				break;
 			case 'p':
-				waldir = pg_strdup(optarg);
+				walpath = pg_strdup(optarg);
 				break;
 			case 'q':
 				config.quiet = true;
@@ -1102,10 +1285,20 @@ main(int argc, char **argv)
 		goto bad_argument;
 	}
 
-	if (waldir != NULL)
+	if (walpath != NULL)
 	{
+		/* validate path points to tar archive */
+		if (is_tar_file(walpath, &compression))
+		{
+			char	   *fname = NULL;
+
+			split_path(walpath, &waldir, &fname);
+
+			private.archive_name = fname;
+			is_tar = true;
+		}
 		/* validate path points to directory */
-		if (!verify_directory(waldir))
+		else if (!verify_directory(walpath))
 		{
 			pg_log_error("could not open directory \"%s\": %m", waldir);
 			goto bad_argument;
@@ -1123,46 +1316,36 @@ main(int argc, char **argv)
 		int			fd;
 		XLogSegNo	segno;
 
+		/*
+		 * If a tar archive is passed using the --path option, all other
+		 * arguments become unnecessary.
+		 */
+		if (is_tar)
+		{
+			pg_log_error("unnecessary command-line arguments specified with tar archive (first is \"%s\")",
+						 argv[optind]);
+			goto bad_argument;
+		}
+
 		split_path(argv[optind], &directory, &fname);
 
-		if (waldir == NULL && directory != NULL)
+		if (walpath == NULL && directory != NULL)
 		{
-			waldir = directory;
+			walpath = directory;
 
-			if (!verify_directory(waldir))
+			if (!verify_directory(walpath))
 				pg_fatal("could not open directory \"%s\": %m", waldir);
 		}
 
-		waldir = identify_target_directory(waldir, fname);
-		fd = open_file_in_directory(waldir, fname);
-		if (fd < 0)
-			pg_fatal("could not open file \"%s\"", fname);
-		close(fd);
-
-		/* parse position from file */
-		XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
-
-		if (XLogRecPtrIsInvalid(private.startptr))
-			XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
-		else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+		if (fname != NULL && is_tar_file(fname, &compression))
 		{
-			pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.startptr),
-						 fname);
-			goto bad_argument;
+			private.archive_name = fname;
+			waldir = walpath ? pg_strdup(walpath) : pg_strdup(".");
+			is_tar = true;
 		}
-
-		/* no second file specified, set end position */
-		if (!(optind + 1 < argc) && XLogRecPtrIsInvalid(private.endptr))
-			XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
-
-		/* parse ENDSEG if passed */
-		if (optind + 1 < argc)
+		else
 		{
-			XLogSegNo	endsegno;
-
-			/* ignore directory, already have that */
-			split_path(argv[optind + 1], &directory, &fname);
+			waldir = identify_target_directory(walpath, fname);
 
 			fd = open_file_in_directory(waldir, fname);
 			if (fd < 0)
@@ -1170,32 +1353,70 @@ main(int argc, char **argv)
 			close(fd);
 
 			/* parse position from file */
-			XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+			XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
 
-			if (endsegno < segno)
-				pg_fatal("ENDSEG %s is before STARTSEG %s",
-						 argv[optind + 1], argv[optind]);
+			if (XLogRecPtrIsInvalid(private.startptr))
+				XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
+			else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+			{
+				pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.startptr),
+							 fname);
+				goto bad_argument;
+			}
 
-			if (XLogRecPtrIsInvalid(private.endptr))
-				XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
-										private.endptr);
+			/* no second file specified, set end position */
+			if (!(optind + 1 < argc) && XLogRecPtrIsInvalid(private.endptr))
+				XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
 
-			/* set segno to endsegno for check of --end */
-			segno = endsegno;
-		}
+			/* parse ENDSEG if passed */
+			if (optind + 1 < argc)
+			{
+				XLogSegNo	endsegno;
+
+				/* ignore directory, already have that */
+				split_path(argv[optind + 1], &directory, &fname);
+
+				fd = open_file_in_directory(waldir, fname);
+				if (fd < 0)
+					pg_fatal("could not open file \"%s\"", fname);
+				close(fd);
+
+				/* parse position from file */
+				XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+
+				if (endsegno < segno)
+					pg_fatal("ENDSEG %s is before STARTSEG %s",
+							 argv[optind + 1], argv[optind]);
 
+				if (XLogRecPtrIsInvalid(private.endptr))
+					XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
+											private.endptr);
 
-		if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
-			private.endptr != (segno + 1) * WalSegSz)
-		{
-			pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.endptr),
-						 argv[argc - 1]);
-			goto bad_argument;
+				/* set segno to endsegno for check of --end */
+				segno = endsegno;
+			}
+
+
+			if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
+				private.endptr != (segno + 1) * WalSegSz)
+			{
+				pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.endptr),
+							 argv[argc - 1]);
+				goto bad_argument;
+			}
 		}
 	}
-	else
-		waldir = identify_target_directory(waldir, NULL);
+	else if (!is_tar)
+		waldir = identify_target_directory(walpath, NULL);
+
+	/* Verify that the archive contains valid WAL files */
+	if (is_tar)
+	{
+		waldir = waldir ? pg_strdup(waldir) : pg_strdup(".");
+		verify_tar_archive(&private, waldir, compression);
+	}
 
 	/* we don't know what to print */
 	if (XLogRecPtrIsInvalid(private.startptr))
@@ -1207,12 +1428,31 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
-	xlogreader_state =
-		XLogReaderAllocate(WalSegSz, waldir,
-						   XL_ROUTINE(.page_read = WALDumpReadPage,
-									  .segment_open = WALDumpOpenSegment,
-									  .segment_close = WALDumpCloseSegment),
-						   &private);
+	if (is_tar)
+	{
+		/* Set up for reading tar file */
+		init_tar_archive_reader(&private, waldir, private.startptr,
+								private.endptr, compression);
+
+		/* Routine to decode WAL files in tar archive */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = TarWALDumpReadPage,
+										  .segment_open = TarWALDumpOpenSegment,
+										  .segment_close = TarWALDumpCloseSegment),
+							   &private);
+	}
+	else
+	{
+		/* Routine to decode WAL files */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = WALDumpReadPage,
+										  .segment_open = WALDumpOpenSegment,
+										  .segment_close = WALDumpCloseSegment),
+							   &private);
+	}
+
 	if (!xlogreader_state)
 		pg_fatal("out of memory while allocating a WAL reading processor");
 
@@ -1321,6 +1561,9 @@ main(int argc, char **argv)
 
 	XLogReaderFree(xlogreader_state);
 
+	if (is_tar)
+		free_tar_archive_reader(&private);
+
 	return EXIT_SUCCESS;
 
 bad_argument:
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 9e62b64ead5..4205e0ef597 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -12,6 +12,8 @@
 #define PG_WALDUMP_H
 
 #include "access/xlogdefs.h"
+#include "fe_utils/astreamer.h"
+#include "lib/stringinfo.h"
 
 extern int	WalSegSz;
 
@@ -22,6 +24,22 @@ typedef struct XLogDumpPrivate
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	bool		endptr_reached;
+
+	/* Fields required to read WAL from archive */
+	char	   *archive_name;	/* Tar archive name */
+	int			archive_fd;		/* File descriptor for the open tar file */
+
+	astreamer  *archive_streamer;
+	StringInfo	archive_streamer_buf;	/* Buffer for receiving WAL data */
+	XLogRecPtr	archive_streamer_read_ptr; /* Populate the buffer with records
+											  until this record pointer */
 } XLogDumpPrivate;
 
-#endif		/* end of PG_WALDUMP_H */
+
+extern astreamer *astreamer_waldump_new(XLogRecPtr startptr,
+										XLogRecPtr endptr,
+										XLogDumpPrivate *privateInfo);
+extern int astreamer_wal_read(char *readBuff, XLogRecPtr startptr, Size count,
+							  XLogDumpPrivate *privateInfo);
+
+#endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 1b712e8d74d..443126a9ce6 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -3,10 +3,13 @@
 
 use strict;
 use warnings FATAL => 'all';
+use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
 
+my $tar = $ENV{TAR};
+
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
 program_options_handling_ok('pg_waldump');
@@ -235,7 +238,7 @@ command_like(
 sub test_pg_waldump
 {
 	local $Test::Builder::Level = $Test::Builder::Level + 1;
-	my @opts = @_;
+	my ($path, @opts) = @_;
 
 	my ($stdout, $stderr);
 
@@ -243,6 +246,7 @@ sub test_pg_waldump
 		'pg_waldump',
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
+		'--path' => $path,
 		@opts
 	  ],
 	  '>' => \$stdout,
@@ -254,11 +258,50 @@ sub test_pg_waldump
 	return @lines;
 }
 
-my @lines;
+# Create a tar archive, sorting the file order
+sub generate_archive
+{
+	my ($archive, $directory, $compression_flags) = @_;
+
+	my @files;
+	opendir my $dh, $directory or die "opendir: $!";
+	while (my $entry = readdir $dh) {
+		# Skip '.' and '..'
+		next if $entry eq '.' || $entry eq '..';
+		push @files, $entry;
+	}
+	closedir $dh;
+
+	@files = sort @files;
+
+	# move into the WAL directory before archiving files
+	my $cwd = getcwd;
+	chdir($directory) || die "chdir: $!";
+	command_ok([$tar, $compression_flags, $archive, @files]);
+	chdir($cwd) || die "chdir: $!";
+}
+
+my $tmp_dir = PostgreSQL::Test::Utils::tempdir_short();
 
 my @scenario = (
 	{
-		'path' => $node->data_dir
+		'path' => $node->data_dir,
+		'is_archive' => 0,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar",
+		'compression_method' => 'none',
+		'compression_flags' => '-cf',
+		'is_archive' => 1,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar.gz",
+		'compression_method' => 'gzip',
+		'compression_flags' => '-czf',
+		'is_archive' => 1,
+		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
 	});
 
 for my $scenario (@scenario)
@@ -267,6 +310,19 @@ for my $scenario (@scenario)
 
 	SKIP:
 	{
+		skip "tar command is not available", 3
+		  if !defined $tar;
+		skip "$scenario->{'compression_method'} compression not supported by this build", 3
+		  if !$scenario->{'enabled'} && $scenario->{'is_archive'};
+
+		  # create pg_wal archive
+		  if ($scenario->{'is_archive'})
+		  {
+			  generate_archive($path,
+				  $node->data_dir . '/pg_wal',
+				  $scenario->{'compression_flags'});
+		  }
+
 		command_fails_like(
 			[ 'pg_waldump', '--path' => $path ],
 			qr/error: no start WAL location given/,
@@ -298,38 +354,42 @@ for my $scenario (@scenario)
 			qr/error: error in WAL record at/,
 			'errors are shown with --quiet');
 
-		@lines = test_pg_waldump('--path' => $path);
+		my @lines;
+		@lines = test_pg_waldump($path);
 		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		@lines = test_pg_waldump($path, '--limit' => 6);
 		is(@lines, 6, 'limit option observed');
 
-		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		@lines = test_pg_waldump($path, '--fullpage');
 		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats');
+		@lines = test_pg_waldump($path, '--stats');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		@lines = test_pg_waldump($path, '--stats=record');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		@lines = test_pg_waldump($path, '--rmgr' => 'Btree');
 		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		@lines = test_pg_waldump($path, '--fork' => 'init');
 		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
 		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
 			0, 'only lines for selected relation');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
 			'--block' => 1);
 		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+
+		# Cleanup.
+		unlink $path if $scenario->{'is_archive'};
 	}
 }
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index a13e8162890..b406ca041ec 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -3444,6 +3444,7 @@ astreamer_recovery_injector
 astreamer_tar_archiver
 astreamer_tar_parser
 astreamer_verify
+astreamer_waldump
 astreamer_zstd_frame
 auth_password_hook_typ
 autovac_table
-- 
2.47.1

From d79a505af9532baae675557de0efb1bcc35d72f5 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Mon, 25 Aug 2025 17:26:29 +0530
Subject: [PATCH v4 5/8] pg_waldump: Remove the restriction on the order of
 archived WAL files.

With previous patch, pg_waldump would stop decoding if WAL files were
not in the required sequence. With this patch, decoding will now
continue.  Any WAL file that is out of order will be written to a
temporary location, from which it will be read later. Once a temporary
file has been read, it will be removed.
---
 doc/src/sgml/ref/pg_waldump.sgml       |   7 +-
 src/bin/pg_waldump/astreamer_waldump.c | 214 +++++++++++++++++++++----
 src/bin/pg_waldump/pg_waldump.c        | 112 ++++++++++++-
 src/bin/pg_waldump/pg_waldump.h        |  30 +++-
 src/bin/pg_waldump/t/001_basic.pl      |   3 +-
 5 files changed, 323 insertions(+), 43 deletions(-)

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index d004bb0f67e..c1afb4097b5 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -149,8 +149,11 @@ PostgreSQL documentation
         of <envar>PGDATA</envar>.
        </para>
        <para>
-        If a tar archive is provided, its WAL segment files must be in
-        sequential order; otherwise, an error will be reported.
+        If a tar archive is provided and its WAL segment files are not in
+        sequential order, those files will be written temporarily. These files
+        will be created inside the directory specified by the <envar>TMPDIR</envar>
+        environment variable if it is set; otherwise, the temporary files will
+        be created within the same directory as the tar archive itself.
        </para>
       </listitem>
      </varlistentry>
diff --git a/src/bin/pg_waldump/astreamer_waldump.c b/src/bin/pg_waldump/astreamer_waldump.c
index caf7da6ccb8..40876c77f6c 100644
--- a/src/bin/pg_waldump/astreamer_waldump.c
+++ b/src/bin/pg_waldump/astreamer_waldump.c
@@ -18,8 +18,8 @@
 
 #include "access/xlog_internal.h"
 #include "access/xlogdefs.h"
+#include "common/file_perm.h"
 #include "common/logging.h"
-#include "fe_utils/simple_list.h"
 #include "pg_waldump.h"
 
 /*
@@ -42,10 +42,11 @@ typedef struct astreamer_waldump
 
 	/* These fields change with archive member. */
 	bool		skipThisSeg;
+	bool		writeThisSeg;
+	FILE	   *segFp;
 	XLogSegNo	nextSegNo;		/* Next expected segment to stream */
 } astreamer_waldump;
 
-static int	astreamer_archive_read(XLogDumpPrivate *privateInfo);
 static void astreamer_waldump_content(astreamer *streamer,
 									  astreamer_member *member,
 									  const char *data, int len,
@@ -56,7 +57,12 @@ static void astreamer_waldump_free(astreamer *streamer);
 static bool member_is_relevant_wal(astreamer_waldump *mystreamer,
 								   astreamer_member *member,
 								   TimeLineID startTimeLineID,
+								   char **curFname,
 								   XLogSegNo *curSegNo);
+static FILE *member_prepare_tmp_write(XLogSegNo curSegNo,
+									  const char *fname);
+static XLogSegNo member_next_segno(XLogSegNo curSegNo,
+								   TimeLineID timeline);
 
 static const astreamer_ops astreamer_waldump_ops = {
 	.content = astreamer_waldump_content,
@@ -164,7 +170,7 @@ astreamer_wal_read(char *readBuff, XLogRecPtr targetPagePtr, Size count,
 /*
  * Reads the archive and passes it to the archive streamer for decompression.
  */
-static int
+int
 astreamer_archive_read(XLogDumpPrivate *privateInfo)
 {
 	int			rc;
@@ -208,17 +214,8 @@ astreamer_waldump_new(XLogRecPtr startptr, XLogRecPtr endPtr,
 	if (XLogRecPtrIsInvalid(startptr))
 		streamer->startSegNo = 0;
 	else
-	{
 		XLByteToSeg(startptr, streamer->startSegNo, WalSegSz);
 
-		/*
-		 * Initialize the record pointer to the beginning of the first
-		 * segment; this pointer will track the WAL record reading status.
-		 */
-		XLogSegNoOffsetToRecPtr(streamer->startSegNo, 0, WalSegSz,
-								privateInfo->archive_streamer_read_ptr);
-	}
-
 	if (XLogRecPtrIsInvalid(endPtr))
 		streamer->endSegNo = UINT64_MAX;
 	else
@@ -247,14 +244,16 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 	{
 		case ASTREAMER_MEMBER_HEADER:
 			{
-				XLogSegNo	segNo;
+				char	   *fname;
 
 				pg_log_debug("pg_waldump: reading \"%s\"", member->pathname);
 
 				mystreamer->skipThisSeg = false;
+				mystreamer->writeThisSeg = false;
 
 				if (!member_is_relevant_wal(mystreamer, member,
-											privateInfo->timeline, &segNo))
+											privateInfo->timeline,
+											&fname, &privateInfo->curSegNo))
 				{
 					mystreamer->skipThisSeg = true;
 					break;
@@ -267,33 +266,67 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 				if (READ_ANY_WAL(mystreamer))
 					break;
 
-				/* WAL segments must be archived in order */
-				if (mystreamer->nextSegNo != segNo)
+				/*
+				 * When WAL segments are not archived sequentially, it becomes
+				 * necessary to write out (or preserve) segments that might be
+				 * required at a later point.
+				 */
+				if (mystreamer->nextSegNo != privateInfo->curSegNo)
 				{
-					pg_log_error("WAL files are not archived in sequential order");
-					pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
-										mystreamer->nextSegNo, segNo);
-					exit(1);
+					mystreamer->writeThisSeg = true;
+					mystreamer->segFp =
+						member_prepare_tmp_write(privateInfo->curSegNo, fname);
+					break;
 				}
 
 				/*
-				 * We track the reading of WAL segment records using a pointer
-				 * that's continuously incremented by the length of the
-				 * received data. This pointer is crucial for serving WAL page
-				 * requests from the WAL decoding routine, so it must be
-				 * accurate.
+				 * If the buffer contains data, the next WAL record must
+				 * logically follow it. Otherwise, this file isn't the one we
+				 * need, and we must export it.
 				 */
-#ifdef USE_ASSERT_CHECKING
-				if (mystreamer->nextSegNo != 0)
+				else if (privateInfo->archive_streamer_buf->len != 0)
 				{
 					XLogRecPtr	recPtr;
 
-					XLogSegNoOffsetToRecPtr(segNo, 0, WalSegSz, recPtr);
-					Assert(privateInfo->archive_streamer_read_ptr == recPtr);
+					XLogSegNoOffsetToRecPtr(privateInfo->curSegNo, 0, WalSegSz,
+											recPtr);
+
+					if (privateInfo->archive_streamer_read_ptr != recPtr)
+					{
+						mystreamer->writeThisSeg = true;
+						mystreamer->segFp =
+							member_prepare_tmp_write(privateInfo->curSegNo, fname);
+
+						/* Update the next expected segment number after this */
+						mystreamer->nextSegNo =
+							member_next_segno(privateInfo->curSegNo + 1,
+											  privateInfo->timeline);
+						break;
+					}
 				}
-#endif
+
+				Assert(!mystreamer->skipThisSeg);
+				Assert(!mystreamer->writeThisSeg);
+
+				/*
+				 * We are now streaming segment containt.
+				 *
+				 * We need to track the reading of WAL segment records using a
+				 * pointer that's typically incremented by the length of the
+				 * data read. However, we sometimes export the WAL file to
+				 * temporary storage, allowing the decoding routine to read
+				 * directly from there. This makes continuous pointer
+				 * incrementing challenging, as file reads can occur from any
+				 * offset, leading to potential errors. Therefore, we now
+				 * reset the pointer when reading from a file for streaming.
+				 */
+				XLogSegNoOffsetToRecPtr(privateInfo->curSegNo, 0, WalSegSz,
+										privateInfo->archive_streamer_read_ptr);
+
 				/* Update the next expected segment number */
-				mystreamer->nextSegNo += 1;
+				mystreamer->nextSegNo =
+					member_next_segno(privateInfo->curSegNo,
+									  privateInfo->timeline);
 			}
 			break;
 
@@ -302,12 +335,45 @@ astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
 			if (mystreamer->skipThisSeg)
 				break;
 
+			/* Or, write contents to file */
+			if (mystreamer->writeThisSeg)
+			{
+				Assert(mystreamer->segFp != NULL);
+
+				errno = 0;
+				if (len > 0 && fwrite(data, len, 1, mystreamer->segFp) != 1)
+				{
+					char	   *fname;
+					int			pathlen = strlen(member->pathname);
+
+					Assert(pathlen >= XLOG_FNAME_LEN);
+
+					fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+
+					/*
+					 * If write didn't set errno, assume problem is no disk
+					 * space
+					 */
+					if (errno == 0)
+						errno = ENOSPC;
+					pg_fatal("could not write to file \"%s\": %m",
+							 get_tmp_wal_file_path(fname));
+				}
+				break;
+			}
+
 			/* Or, copy contents to buffer */
 			privateInfo->archive_streamer_read_ptr += len;
 			astreamer_buffer_bytes(streamer, &data, &len, len);
 			break;
 
 		case ASTREAMER_MEMBER_TRAILER:
+			if (mystreamer->segFp != NULL)
+			{
+				fclose(mystreamer->segFp);
+				mystreamer->segFp = NULL;
+			}
+			privateInfo->curSegNo = 0;
 			break;
 
 		case ASTREAMER_ARCHIVE_TRAILER:
@@ -334,8 +400,14 @@ astreamer_waldump_finalize(astreamer *streamer)
 static void
 astreamer_waldump_free(astreamer *streamer)
 {
+	astreamer_waldump *mystreamer;
+
 	Assert(streamer->bbs_next == NULL);
 
+	mystreamer = (astreamer_waldump *) streamer;
+	if (mystreamer->segFp != NULL)
+		fclose(mystreamer->segFp);
+
 	pfree(streamer->bbs_buffer.data);
 	pfree(streamer);
 }
@@ -347,7 +419,8 @@ astreamer_waldump_free(astreamer *streamer)
  */
 static bool
 member_is_relevant_wal(astreamer_waldump *mystreamer, astreamer_member *member,
-					   TimeLineID startTimeLineID, XLogSegNo *curSegNo)
+					   TimeLineID startTimeLineID, char **curFname,
+					   XLogSegNo *curSegNo)
 {
 	int			pathlen;
 	XLogSegNo	segNo;
@@ -382,7 +455,84 @@ member_is_relevant_wal(astreamer_waldump *mystreamer, astreamer_member *member,
 			return false;
 	}
 
+	*curFname = fname;
 	*curSegNo = segNo;
 
 	return true;
 }
+
+/*
+ * Create an empty placeholder file and return its handle.  The file is also
+ * added to an exported list for future management, e.g.  access, deletion, and
+ * existence checks.
+ */
+static FILE *
+member_prepare_tmp_write(XLogSegNo curSegNo, const char *fname)
+{
+	FILE	   *file;
+	char	   *fpath = get_tmp_wal_file_path(fname);
+
+	/* Create an empty placeholder */
+	file = fopen(fpath, PG_BINARY_W);
+	if (file == NULL)
+		pg_fatal("could not create file \"%s\": %m", fpath);
+
+#ifndef WIN32
+	if (chmod(fpath, pg_file_create_mode))
+		pg_fatal("could not set permissions on file \"%s\": %m",
+				 fpath);
+#endif
+
+	pg_log_info("temporarily exporting file \"%s\"", fpath);
+
+	/* Record this segment's export */
+	simple_string_list_append(&TmpWalSegList, fname);
+	pfree(fpath);
+
+	return file;
+}
+
+/*
+ * Get next WAL segment that needs to be retrieved from the archive.
+ *
+ * The function checks for the presence of a previously read and extracted WAL
+ * segment in the temporary storage. If a temporary file is found for that
+ * segment, it indicates the segment has already been successfully retrieved
+ * from the archive. In this case, the function increments the segment number
+ * and repeats the check. This process continues until a segment that has not
+ * yet been retrieved is found, at which point the function returns its number.
+ */
+static XLogSegNo
+member_next_segno(XLogSegNo curSegNo, TimeLineID timeline)
+{
+	XLogSegNo	nextSegNo = curSegNo + 1;
+	bool		exists;
+
+	/*
+	 * If we find a file that was previously written to the temporary space,
+	 * it indicates that the corresponding WAL segment request has already
+	 * been fulfilled. In that case, we increment the nextSegNo counter and
+	 * check again whether that segment number again. if found above steps
+	 * will be return if not then we return that segment number which would be
+	 * needed from the archive.
+	 */
+	do
+	{
+		char		fname[MAXFNAMELEN];
+
+		XLogFileName(fname, timeline, nextSegNo, WalSegSz);
+
+		/*
+		 * If the WAL segment has already been exported, increment the counter
+		 * and check for the next segment.
+		 */
+		exists = false;
+		if (simple_string_list_member(&TmpWalSegList, fname))
+		{
+			nextSegNo += 1;
+			exists = true;
+		}
+	} while (exists);
+
+	return nextSegNo;
+}
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 393d6bfa9ef..615227b691c 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -43,6 +43,10 @@ static const char *progname;
 int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 static volatile sig_atomic_t time_to_stop = false;
 
+/* Temporary exported WAL file directory and the list */
+char	   *TmpWalSegDir = NULL;
+SimpleStringList TmpWalSegList = {NULL, NULL};
+
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
 typedef struct XLogDumpConfig
@@ -360,6 +364,41 @@ is_tar_file(const char *fname, pg_compress_algorithm *compression)
 	return true;
 }
 
+/*
+ * Set up a temporary directory to temporarily store WAL segments.
+ */
+static void
+setup_tmp_walseg_dir(const char *waldir)
+{
+	/*
+	 * Use the directory specified by the TEMDIR environment variable. If it's
+	 * not set, use the provided WAL directory.
+	 */
+	TmpWalSegDir = getenv("TMPDIR") ?
+		pg_strdup(getenv("TMPDIR")) : pg_strdup(waldir);
+	canonicalize_path(TmpWalSegDir);
+}
+
+/*
+ * Removes the temporarily store WAL segments, if any at exiting.
+ */
+static void
+remove_tmp_walseg_dir_atexit(void)
+{
+	SimpleStringListCell *cell;
+
+	/* Clear out any existing temporary files */
+	for (cell = TmpWalSegList.head; cell; cell = cell->next)
+	{
+		char	   *fpath = get_tmp_wal_file_path(cell->val);
+
+		if (unlink(fpath) == 0)
+			pg_log_info("removed file \"%s\"", fpath);
+		pfree(fpath);
+	}
+}
+
+
 /*
  * Initializes the tar archive reader and a temporary directory for WAL files.
  */
@@ -404,6 +443,7 @@ init_tar_archive_reader(XLogDumpPrivate *private, const char *waldir,
 		streamer = astreamer_zstd_decompressor_new(streamer);
 
 	private->archive_streamer = streamer;
+	private->curSegNo = 0;
 }
 
 /*
@@ -548,7 +588,7 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = required_read_len(private, targetPtr, reqLen);
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
 	if (private->endptr_reached)
@@ -607,12 +647,70 @@ TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				   XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = required_read_len(private, targetPtr, reqLen);
+	int			count = required_read_len(private, targetPagePtr, reqLen);
+	XLogSegNo	nextSegNo;
 
 	if (private->endptr_reached)
 		return -1;
 
-	/* Read the WAL page from the archive streamer */
+	/*
+	 * If the target page is in a different segment, first check for the WAL
+	 * segment's physical existence in the temporary directory.
+	 */
+	nextSegNo = state->seg.ws_segno;
+	if (!XLByteInSeg(targetPagePtr, nextSegNo, WalSegSz))
+	{
+		char		fname[MAXFNAMELEN];
+		char	   *fpath;
+
+		if (state->seg.ws_file >= 0)
+		{
+			close(state->seg.ws_file);
+			state->seg.ws_file = -1;
+
+			/* Remove this file, as it is no longer needed. */
+			XLogFileName(fname, state->seg.ws_tli, nextSegNo, WalSegSz);
+			fpath = get_tmp_wal_file_path(fname);
+			pg_log_info("removing file \"%s\"", fpath);
+			unlink(fpath);
+			pfree(fpath);
+		}
+
+		XLByteToSeg(targetPagePtr, nextSegNo, WalSegSz);
+		state->seg.ws_tli = private->timeline;
+		state->seg.ws_segno = nextSegNo;
+
+		/*
+		 * If the next segment exists, open it and continue reading from there
+		 */
+		XLogFileName(fname, private->timeline, nextSegNo, WalSegSz);
+		if (simple_string_list_member(&TmpWalSegList, fname))
+		{
+			fpath = get_tmp_wal_file_path(fname);
+			state->seg.ws_file = open(fpath, O_RDONLY | PG_BINARY, 0);
+
+			if (state->seg.ws_file < 0)
+				pg_fatal("could not open file \"%s\": %m", fpath);
+			pfree(fpath);
+		}
+	}
+
+	/* Continue reading from the open WAL segment, if any */
+	if (state->seg.ws_file >= 0)
+	{
+		/*
+		 * To prevent a race condition where the archive streamer is still
+		 * exporting a file that we are trying to read, we invoke the streamer
+		 * to ensure enough data is available.
+		 */
+		if (private->curSegNo == state->seg.ws_segno)
+			astreamer_archive_read(private);
+
+		return WALDumpReadPage(state, targetPagePtr, reqLen, targetPtr,
+							   readBuff);
+	}
+
+	/* Otherwise, read the WAL page from the archive streamer */
 	return astreamer_wal_read(readBuff, targetPagePtr, count, private);
 }
 
@@ -1340,7 +1438,6 @@ main(int argc, char **argv)
 		if (fname != NULL && is_tar_file(fname, &compression))
 		{
 			private.archive_name = fname;
-			waldir = walpath ? pg_strdup(walpath) : pg_strdup(".");
 			is_tar = true;
 		}
 		else
@@ -1434,6 +1531,13 @@ main(int argc, char **argv)
 		init_tar_archive_reader(&private, waldir, private.startptr,
 								private.endptr, compression);
 
+		/*
+		 * Setup temporary directory to store WAL segments and set up an exit
+		 * callback to remove it upon completion.
+		 */
+		setup_tmp_walseg_dir(waldir);
+		atexit(remove_tmp_walseg_dir_atexit);
+
 		/* Routine to decode WAL files in tar archive */
 		xlogreader_state =
 			XLogReaderAllocate(WalSegSz, waldir,
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 4205e0ef597..1a1cf35e6f3 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -13,9 +13,14 @@
 
 #include "access/xlogdefs.h"
 #include "fe_utils/astreamer.h"
+#include "fe_utils/simple_list.h"
 #include "lib/stringinfo.h"
 
+#define TEMP_FILE_EXT	"waldump.tmp"
+
 extern int	WalSegSz;
+extern char *TmpWalSegDir;
+extern SimpleStringList TmpWalSegList;
 
 /* Contains the necessary information to drive WAL decoding */
 typedef struct XLogDumpPrivate
@@ -31,15 +36,32 @@ typedef struct XLogDumpPrivate
 
 	astreamer  *archive_streamer;
 	StringInfo	archive_streamer_buf;	/* Buffer for receiving WAL data */
-	XLogRecPtr	archive_streamer_read_ptr; /* Populate the buffer with records
-											  until this record pointer */
+	XLogRecPtr	archive_streamer_read_ptr;	/* Populate the buffer with
+											 * records until this record
+											 * pointer */
+	XLogSegNo	curSegNo;		/* Current segment being read */
 } XLogDumpPrivate;
 
+/*
+ * Generate the temporary WAL file path.
+ *
+ * Note that the caller is responsible to pfree it.
+ */
+static inline char *
+get_tmp_wal_file_path(const char *fname)
+{
+	char	   *fpath = (char *) palloc(MAXPGPATH);
 
-extern astreamer *astreamer_waldump_new(XLogRecPtr startptr,
-										XLogRecPtr endptr,
+	snprintf(fpath, MAXPGPATH, "%s/%s.%s", TmpWalSegDir, fname,
+			 TEMP_FILE_EXT);
+
+	return fpath;
+}
+
+extern astreamer *astreamer_waldump_new(XLogRecPtr startptr, XLogRecPtr endptr,
 										XLogDumpPrivate *privateInfo);
 extern int astreamer_wal_read(char *readBuff, XLogRecPtr startptr, Size count,
 							  XLogDumpPrivate *privateInfo);
+extern int astreamer_archive_read(XLogDumpPrivate *privateInfo);
 
 #endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 443126a9ce6..d5fa1f6d28d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -7,6 +7,7 @@ use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
+use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
 
@@ -272,7 +273,7 @@ sub generate_archive
 	}
 	closedir $dh;
 
-	@files = sort @files;
+	@files = shuffle @files;
 
 	# move into the WAL directory before archiving files
 	my $cwd = getcwd;
-- 
2.47.1

From 9c768466e35384d3366abd6ce0d04b6932116256 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 14:47:43 +0530
Subject: [PATCH v4 6/8] pg_verifybackup: Delay default WAL directory
 preparation.

We are not sure whether to parse WAL from a directory or an archive
until the backup format is known. Therefore, we delay preparing the
default WAL directory until the point of parsing. This delay is
harmless, as the WAL directory is not used elsewhere.
---
 src/bin/pg_verifybackup/pg_verifybackup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 5e6c13bb921..31ebc1581fb 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -285,10 +285,6 @@ main(int argc, char **argv)
 		manifest_path = psprintf("%s/backup_manifest",
 								 context.backup_directory);
 
-	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
-
 	/*
 	 * Try to read the manifest. We treat any errors encountered while parsing
 	 * the manifest as fatal; there doesn't seem to be much point in trying to
@@ -368,6 +364,10 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
+	/* By default, look for the WAL in the backup directory, too. */
+	if (wal_directory == NULL)
+		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
-- 
2.47.1

From 43c598c482171e1c5d764ead6614c95104207aa4 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 24 Jul 2025 16:37:43 +0530
Subject: [PATCH v4 7/8] pg_verifybackup: Rename the wal-directory switch to
 wal-path

With previous patches to pg_waldump can now decode WAL directly from
tar files.  This means you'll be able to specify a tar archive path
instead of a traditional WAL directory.

To keep things consistent and more versatile, we should also
generalize the input switch for pg_verifybackup. It should accept
either a directory or a tar file path that contains WALs. This change
will also aligning it with the existing manifest-path switch naming.
---
 doc/src/sgml/ref/pg_verifybackup.sgml     |  2 +-
 src/bin/pg_verifybackup/pg_verifybackup.c | 22 +++++++++++-----------
 src/bin/pg_verifybackup/po/de.po          |  4 ++--
 src/bin/pg_verifybackup/po/el.po          |  4 ++--
 src/bin/pg_verifybackup/po/es.po          |  4 ++--
 src/bin/pg_verifybackup/po/fr.po          |  4 ++--
 src/bin/pg_verifybackup/po/it.po          |  4 ++--
 src/bin/pg_verifybackup/po/ja.po          |  4 ++--
 src/bin/pg_verifybackup/po/ka.po          |  4 ++--
 src/bin/pg_verifybackup/po/ko.po          |  4 ++--
 src/bin/pg_verifybackup/po/ru.po          |  4 ++--
 src/bin/pg_verifybackup/po/sv.po          |  4 ++--
 src/bin/pg_verifybackup/po/uk.po          |  4 ++--
 src/bin/pg_verifybackup/po/zh_CN.po       |  4 ++--
 src/bin/pg_verifybackup/po/zh_TW.po       |  4 ++--
 src/bin/pg_verifybackup/t/007_wal.pl      |  4 ++--
 16 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index 61c12975e4a..e9b8bfd51b1 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -261,7 +261,7 @@ PostgreSQL documentation
 
      <varlistentry>
       <term><option>-w <replaceable class="parameter">path</replaceable></option></term>
-      <term><option>--wal-directory=<replaceable class="parameter">path</replaceable></option></term>
+      <term><option>--wal-path=<replaceable class="parameter">path</replaceable></option></term>
       <listitem>
        <para>
         Try to parse WAL files stored in the specified directory, rather than
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 31ebc1581fb..1ee400199da 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -93,7 +93,7 @@ static void verify_file_checksum(verifier_context *context,
 								 uint8 *buffer);
 static void parse_required_wal(verifier_context *context,
 							   char *pg_waldump_path,
-							   char *wal_directory);
+							   char *wal_path);
 static astreamer *create_archive_verifier(verifier_context *context,
 										  char *archive_name,
 										  Oid tblspc_oid,
@@ -126,7 +126,7 @@ main(int argc, char **argv)
 		{"progress", no_argument, NULL, 'P'},
 		{"quiet", no_argument, NULL, 'q'},
 		{"skip-checksums", no_argument, NULL, 's'},
-		{"wal-directory", required_argument, NULL, 'w'},
+		{"wal-path", required_argument, NULL, 'w'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -135,7 +135,7 @@ main(int argc, char **argv)
 	char	   *manifest_path = NULL;
 	bool		no_parse_wal = false;
 	bool		quiet = false;
-	char	   *wal_directory = NULL;
+	char	   *wal_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -221,8 +221,8 @@ main(int argc, char **argv)
 				context.skip_checksums = true;
 				break;
 			case 'w':
-				wal_directory = pstrdup(optarg);
-				canonicalize_path(wal_directory);
+				wal_path = pstrdup(optarg);
+				canonicalize_path(wal_path);
 				break;
 			default:
 				/* getopt_long already emitted a complaint */
@@ -365,15 +365,15 @@ main(int argc, char **argv)
 		verify_backup_checksums(&context);
 
 	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+	if (wal_path == NULL)
+		wal_path = psprintf("%s/pg_wal", context.backup_directory);
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
 	 */
 	if (!no_parse_wal)
-		parse_required_wal(&context, pg_waldump_path, wal_directory);
+		parse_required_wal(&context, pg_waldump_path, wal_path);
 
 	/*
 	 * If everything looks OK, tell the user this, unless we were asked to
@@ -1198,7 +1198,7 @@ verify_file_checksum(verifier_context *context, manifest_file *m,
  */
 static void
 parse_required_wal(verifier_context *context, char *pg_waldump_path,
-				   char *wal_directory)
+				   char *wal_path)
 {
 	manifest_data *manifest = context->manifest;
 	manifest_wal_range *this_wal_range = manifest->first_wal_range;
@@ -1208,7 +1208,7 @@ parse_required_wal(verifier_context *context, char *pg_waldump_path,
 		char	   *pg_waldump_cmd;
 
 		pg_waldump_cmd = psprintf("\"%s\" --quiet --path=\"%s\" --timeline=%u --start=%X/%08X --end=%X/%08X\n",
-								  pg_waldump_path, wal_directory, this_wal_range->tli,
+								  pg_waldump_path, wal_path, this_wal_range->tli,
 								  LSN_FORMAT_ARGS(this_wal_range->start_lsn),
 								  LSN_FORMAT_ARGS(this_wal_range->end_lsn));
 		fflush(NULL);
@@ -1376,7 +1376,7 @@ usage(void)
 	printf(_("  -P, --progress              show progress information\n"));
 	printf(_("  -q, --quiet                 do not print any output, except for errors\n"));
 	printf(_("  -s, --skip-checksums        skip checksum verification\n"));
-	printf(_("  -w, --wal-directory=PATH    use specified path for WAL files\n"));
+	printf(_("  -w, --wal-path=PATH         use specified path for WAL files\n"));
 	printf(_("  -V, --version               output version information, then exit\n"));
 	printf(_("  -?, --help                  show this help, then exit\n"));
 	printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
diff --git a/src/bin/pg_verifybackup/po/de.po b/src/bin/pg_verifybackup/po/de.po
index a9e24931100..9b5cd5898cf 100644
--- a/src/bin/pg_verifybackup/po/de.po
+++ b/src/bin/pg_verifybackup/po/de.po
@@ -785,8 +785,8 @@ msgstr "  -s, --skip-checksums        Überprüfung der Prüfsummen überspringe
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/el.po b/src/bin/pg_verifybackup/po/el.po
index 3e3f20c67c5..81442f51c17 100644
--- a/src/bin/pg_verifybackup/po/el.po
+++ b/src/bin/pg_verifybackup/po/el.po
@@ -494,8 +494,8 @@ msgstr "  -s, --skip-checksums        παράκαμψε την επαλήθευ
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/es.po b/src/bin/pg_verifybackup/po/es.po
index 0cb958f3448..7f729fa35ba 100644
--- a/src/bin/pg_verifybackup/po/es.po
+++ b/src/bin/pg_verifybackup/po/es.po
@@ -495,8 +495,8 @@ msgstr "  -s, --skip-checksums        omitir la verificación de la suma de comp
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    utilizar la ruta especificada para los archivos WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    utilizar la ruta especificada para los archivos WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/fr.po b/src/bin/pg_verifybackup/po/fr.po
index da8c72f6427..09937966fa7 100644
--- a/src/bin/pg_verifybackup/po/fr.po
+++ b/src/bin/pg_verifybackup/po/fr.po
@@ -498,8 +498,8 @@ msgstr "  -s, --skip-checksums        ignore la vérification des sommes de cont
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/it.po b/src/bin/pg_verifybackup/po/it.po
index 317b0b71e7f..4da68d0074e 100644
--- a/src/bin/pg_verifybackup/po/it.po
+++ b/src/bin/pg_verifybackup/po/it.po
@@ -472,8 +472,8 @@ msgstr "  -s, --skip-checksums         salta la verifica del checksum\n"
 
 #: pg_verifybackup.c:911
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH     usa il percorso specificato per i file WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH     usa il percorso specificato per i file WAL\n"
 
 #: pg_verifybackup.c:912
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ja.po b/src/bin/pg_verifybackup/po/ja.po
index c910fb236cc..a948959b54f 100644
--- a/src/bin/pg_verifybackup/po/ja.po
+++ b/src/bin/pg_verifybackup/po/ja.po
@@ -672,8 +672,8 @@ msgstr "  -s, --skip-checksums        チェックサム検証をスキップ\n"
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    WALファイルに指定したパスを使用する\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    WALファイルに指定したパスを使用する\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ka.po b/src/bin/pg_verifybackup/po/ka.po
index 982751984c7..ef2799316a8 100644
--- a/src/bin/pg_verifybackup/po/ka.po
+++ b/src/bin/pg_verifybackup/po/ka.po
@@ -784,8 +784,8 @@ msgstr "  -s, --skip-checksums        საკონტროლო ჯამ
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ko.po b/src/bin/pg_verifybackup/po/ko.po
index acdc3da5e02..eaf91ef1e98 100644
--- a/src/bin/pg_verifybackup/po/ko.po
+++ b/src/bin/pg_verifybackup/po/ko.po
@@ -501,8 +501,8 @@ msgstr "  -s, --skip-checksums        체크섬 검사 건너뜀\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=경로    WAL 파일이 있는 경로 지정\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=경로    WAL 파일이 있는 경로 지정\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ru.po b/src/bin/pg_verifybackup/po/ru.po
index 64005feedfd..7fb0e5ab1f6 100644
--- a/src/bin/pg_verifybackup/po/ru.po
+++ b/src/bin/pg_verifybackup/po/ru.po
@@ -507,9 +507,9 @@ msgstr "  -s, --skip-checksums        пропустить проверку ко
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
 msgstr ""
-"  -w, --wal-directory=ПУТЬ    использовать заданный путь к файлам WAL\n"
+"  -w, --wal-path=ПУТЬ    использовать заданный путь к файлам WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/sv.po b/src/bin/pg_verifybackup/po/sv.po
index 17240feeb5c..97125838e8c 100644
--- a/src/bin/pg_verifybackup/po/sv.po
+++ b/src/bin/pg_verifybackup/po/sv.po
@@ -492,8 +492,8 @@ msgstr "  -s, --skip-checksums        hoppa över verifiering av kontrollsummor\
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=SÖKVÄG  använd denna sökväg till WAL-filer\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=SÖKVÄG  använd denna sökväg till WAL-filer\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/uk.po b/src/bin/pg_verifybackup/po/uk.po
index 034b9764232..63f8041ab38 100644
--- a/src/bin/pg_verifybackup/po/uk.po
+++ b/src/bin/pg_verifybackup/po/uk.po
@@ -484,8 +484,8 @@ msgstr "  -s, --skip-checksums не перевіряти контрольні с
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH використовувати вказаний шлях для файлів WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH використовувати вказаний шлях для файлів WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_CN.po b/src/bin/pg_verifybackup/po/zh_CN.po
index b7d97c8976d..fb6fcae8b82 100644
--- a/src/bin/pg_verifybackup/po/zh_CN.po
+++ b/src/bin/pg_verifybackup/po/zh_CN.po
@@ -465,8 +465,8 @@ msgstr "  -s, --skip-checksums        跳过校验和验证\n"
 
 #: pg_verifybackup.c:919
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    对WAL文件使用指定路径\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    对WAL文件使用指定路径\n"
 
 #: pg_verifybackup.c:920
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_TW.po b/src/bin/pg_verifybackup/po/zh_TW.po
index c1b710b0a36..568f972b0bb 100644
--- a/src/bin/pg_verifybackup/po/zh_TW.po
+++ b/src/bin/pg_verifybackup/po/zh_TW.po
@@ -555,8 +555,8 @@ msgstr "  -s, --skip-checksums        跳過檢查碼驗證\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    用指定的路徑存放 WAL 檔\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    用指定的路徑存放 WAL 檔\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/t/007_wal.pl b/src/bin/pg_verifybackup/t/007_wal.pl
index babc4f0a86b..b07f80719b0 100644
--- a/src/bin/pg_verifybackup/t/007_wal.pl
+++ b/src/bin/pg_verifybackup/t/007_wal.pl
@@ -42,10 +42,10 @@ command_ok([ 'pg_verifybackup', '--no-parse-wal', $backup_path ],
 command_ok(
 	[
 		'pg_verifybackup',
-		'--wal-directory' => $relocated_pg_wal,
+		'--wal-path' => $relocated_pg_wal,
 		$backup_path
 	],
-	'--wal-directory can be used to specify WAL directory');
+	'--wal-path can be used to specify WAL directory');
 
 # Move directory back to original location.
 rename($relocated_pg_wal, $original_pg_wal) || die "rename pg_wal back: $!";
-- 
2.47.1

From ca9b3ccec8143a53c2dbcae3a11a0edf09f5b96b Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 17 Jul 2025 16:39:36 +0530
Subject: [PATCH v4 8/8] pg_verifybackup: enabled WAL parsing for tar-format
 backup

Now that pg_waldump supports decoding from tar archives, we should
leverage this functionality to remove the previous restriction on WAL
parsing for tar-backed formats.
---
 doc/src/sgml/ref/pg_verifybackup.sgml         |  5 +-
 src/bin/pg_verifybackup/pg_verifybackup.c     | 66 +++++++++++++------
 src/bin/pg_verifybackup/t/002_algorithm.pl    |  4 --
 src/bin/pg_verifybackup/t/003_corruption.pl   |  4 +-
 src/bin/pg_verifybackup/t/008_untar.pl        |  3 +-
 src/bin/pg_verifybackup/t/010_client_untar.pl |  3 +-
 6 files changed, 50 insertions(+), 35 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index e9b8bfd51b1..16b50b5a4df 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -36,10 +36,7 @@ PostgreSQL documentation
    <literal>backup_manifest</literal> generated by the server at the time
    of the backup. The backup may be stored either in the "plain" or the "tar"
    format; this includes tar-format backups compressed with any algorithm
-   supported by <application>pg_basebackup</application>. However, at present,
-   <literal>WAL</literal> verification is supported only for plain-format
-   backups. Therefore, if the backup is stored in tar-format, the
-   <literal>-n, --no-parse-wal</literal> option should be used.
+   supported by <application>pg_basebackup</application>.
   </para>
 
   <para>
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 1ee400199da..4bfe6fdff16 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -74,7 +74,9 @@ pg_noreturn static void report_manifest_error(JsonManifestParseContext *context,
 											  const char *fmt,...)
 			pg_attribute_printf(2, 3);
 
-static void verify_tar_backup(verifier_context *context, DIR *dir);
+static void verify_tar_backup(verifier_context *context, DIR *dir,
+							  char **base_archive_path,
+							  char **wal_archive_path);
 static void verify_plain_backup_directory(verifier_context *context,
 										  char *relpath, char *fullpath,
 										  DIR *dir);
@@ -83,7 +85,9 @@ static void verify_plain_backup_file(verifier_context *context, char *relpath,
 static void verify_control_file(const char *controlpath,
 								uint64 manifest_system_identifier);
 static void precheck_tar_backup_file(verifier_context *context, char *relpath,
-									 char *fullpath, SimplePtrList *tarfiles);
+									 char *fullpath, SimplePtrList *tarfiles,
+									 char **base_archive_path,
+									 char **wal_archive_path);
 static void verify_tar_file(verifier_context *context, char *relpath,
 							char *fullpath, astreamer *streamer);
 static void report_extra_backup_files(verifier_context *context);
@@ -136,6 +140,8 @@ main(int argc, char **argv)
 	bool		no_parse_wal = false;
 	bool		quiet = false;
 	char	   *wal_path = NULL;
+	char	   *base_archive_path = NULL;
+	char	   *wal_archive_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -327,17 +333,6 @@ main(int argc, char **argv)
 		pfree(path);
 	}
 
-	/*
-	 * XXX: In the future, we should consider enhancing pg_waldump to read WAL
-	 * files from an archive.
-	 */
-	if (!no_parse_wal && context.format == 't')
-	{
-		pg_log_error("pg_waldump cannot read tar files");
-		pg_log_error_hint("You must use -n/--no-parse-wal when verifying a tar-format backup.");
-		exit(1);
-	}
-
 	/*
 	 * Perform the appropriate type of verification appropriate based on the
 	 * backup format. This will close 'dir'.
@@ -346,7 +341,7 @@ main(int argc, char **argv)
 		verify_plain_backup_directory(&context, NULL, context.backup_directory,
 									  dir);
 	else
-		verify_tar_backup(&context, dir);
+		verify_tar_backup(&context, dir, &base_archive_path, &wal_archive_path);
 
 	/*
 	 * The "matched" flag should now be set on every entry in the hash table.
@@ -364,9 +359,28 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
-	/* By default, look for the WAL in the backup directory, too. */
+	/*
+	 * By default, WAL files are expected to be found in the backup directory
+	 * for plain-format backups. In the case of tar-format backups, if a
+	 * separate WAL archive is not found, the WAL files are most likely
+	 * included within the main data directory archive.
+	 */
 	if (wal_path == NULL)
-		wal_path = psprintf("%s/pg_wal", context.backup_directory);
+	{
+		if (context.format == 'p')
+			wal_path = psprintf("%s/pg_wal", context.backup_directory);
+		else if (wal_archive_path)
+			wal_path = wal_archive_path;
+		else if (base_archive_path)
+			wal_path = base_archive_path;
+		else
+		{
+			pg_log_error("wal archive not found");
+			pg_log_error_hint("Specify the correct path using the option -w/--wal-path."
+							  "Or you must use -n/--no-parse-wal when verifying a tar-format backup.");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
@@ -787,7 +801,8 @@ verify_control_file(const char *controlpath, uint64 manifest_system_identifier)
  * close when we're done with it.
  */
 static void
-verify_tar_backup(verifier_context *context, DIR *dir)
+verify_tar_backup(verifier_context *context, DIR *dir, char **base_archive_path,
+				  char **wal_archive_path)
 {
 	struct dirent *dirent;
 	SimplePtrList tarfiles = {NULL, NULL};
@@ -816,7 +831,8 @@ verify_tar_backup(verifier_context *context, DIR *dir)
 			char	   *fullpath;
 
 			fullpath = psprintf("%s/%s", context->backup_directory, filename);
-			precheck_tar_backup_file(context, filename, fullpath, &tarfiles);
+			precheck_tar_backup_file(context, filename, fullpath, &tarfiles,
+									 base_archive_path, wal_archive_path);
 			pfree(fullpath);
 		}
 	}
@@ -875,11 +891,13 @@ verify_tar_backup(verifier_context *context, DIR *dir)
  *
  * The arguments to this function are mostly the same as the
  * verify_plain_backup_file. The additional argument outputs a list of valid
- * tar files.
+ * tar files, along with the full paths to the main archive and the WAL
+ * directory archive.
  */
 static void
 precheck_tar_backup_file(verifier_context *context, char *relpath,
-						 char *fullpath, SimplePtrList *tarfiles)
+						 char *fullpath, SimplePtrList *tarfiles,
+						 char **base_archive_path, char **wal_archive_path)
 {
 	struct stat sb;
 	Oid			tblspc_oid = InvalidOid;
@@ -918,9 +936,17 @@ precheck_tar_backup_file(verifier_context *context, char *relpath,
 	 * extension such as .gz, .lz4, or .zst.
 	 */
 	if (strncmp("base", relpath, 4) == 0)
+	{
 		suffix = relpath + 4;
+
+		*base_archive_path = pstrdup(fullpath);
+	}
 	else if (strncmp("pg_wal", relpath, 6) == 0)
+	{
 		suffix = relpath + 6;
+
+		*wal_archive_path = pstrdup(fullpath);
+	}
 	else
 	{
 		/* Expected a <tablespaceoid>.tar file here. */
diff --git a/src/bin/pg_verifybackup/t/002_algorithm.pl b/src/bin/pg_verifybackup/t/002_algorithm.pl
index ae16c11bc4d..4f284a9e828 100644
--- a/src/bin/pg_verifybackup/t/002_algorithm.pl
+++ b/src/bin/pg_verifybackup/t/002_algorithm.pl
@@ -30,10 +30,6 @@ sub test_checksums
 	{
 		# Add switch to get a tar-format backup
 		push @backup, ('--format' => 'tar');
-
-		# Add switch to skip WAL verification, which is not yet supported for
-		# tar-format backups
-		push @verify, ('--no-parse-wal');
 	}
 
 	# A backup with a bogus algorithm should fail.
diff --git a/src/bin/pg_verifybackup/t/003_corruption.pl b/src/bin/pg_verifybackup/t/003_corruption.pl
index 1dd60f709cf..f1ebdbb46b4 100644
--- a/src/bin/pg_verifybackup/t/003_corruption.pl
+++ b/src/bin/pg_verifybackup/t/003_corruption.pl
@@ -193,10 +193,8 @@ for my $scenario (@scenario)
 			command_ok([ $tar, '-cf' => "$tar_backup_path/base.tar", '.' ]);
 			chdir($cwd) || die "chdir: $!";
 
-			# Now check that the backup no longer verifies. We must use -n
-			# here, because pg_waldump can't yet read WAL from a tarfile.
 			command_fails_like(
-				[ 'pg_verifybackup', '--no-parse-wal', $tar_backup_path ],
+				[ 'pg_verifybackup', $tar_backup_path ],
 				$scenario->{'fails_like'},
 				"corrupt backup fails verification: $name");
 
diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index bc3d6b352ad..0cfe1f9532c 100644
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -123,8 +123,7 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index b62faeb5acf..76269a73673 100644
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -137,8 +137,7 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
-- 
2.47.1

From 9bfed15797bcecf15e828d2b48f64caead36e9bb Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 24 Jun 2025 11:33:20 +0530
Subject: [PATCH v5 1/8] Refactor: pg_waldump: Move some declarations to new
 pg_waldump.h

This change prepares for a second source file in this directory to
support reading WAL from tar files. Common structures, declarations,
and functions are being exported through this include file so
they can be used in both files.
---
 src/bin/pg_waldump/pg_waldump.c | 11 ++---------
 src/bin/pg_waldump/pg_waldump.h | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 9 deletions(-)
 create mode 100644 src/bin/pg_waldump/pg_waldump.h

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 13d3ec2f5be..a49b2fd96c7 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -29,6 +29,7 @@
 #include "common/logging.h"
 #include "common/relpath.h"
 #include "getopt_long.h"
+#include "pg_waldump.h"
 #include "rmgrdesc.h"
 #include "storage/bufpage.h"
 
@@ -39,19 +40,11 @@
 
 static const char *progname;
 
-static int	WalSegSz;
+int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 static volatile sig_atomic_t time_to_stop = false;
 
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
-typedef struct XLogDumpPrivate
-{
-	TimeLineID	timeline;
-	XLogRecPtr	startptr;
-	XLogRecPtr	endptr;
-	bool		endptr_reached;
-} XLogDumpPrivate;
-
 typedef struct XLogDumpConfig
 {
 	/* display options */
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
new file mode 100644
index 00000000000..9e62b64ead5
--- /dev/null
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -0,0 +1,27 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_waldump.h - decode and display WAL
+ *
+ * Copyright (c) 2013-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  src/bin/pg_waldump/pg_waldump.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_WALDUMP_H
+#define PG_WALDUMP_H
+
+#include "access/xlogdefs.h"
+
+extern int	WalSegSz;
+
+/* Contains the necessary information to drive WAL decoding */
+typedef struct XLogDumpPrivate
+{
+	TimeLineID	timeline;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
+	bool		endptr_reached;
+} XLogDumpPrivate;
+
+#endif		/* end of PG_WALDUMP_H */
-- 
2.47.1

From 830dcb9c9f98de3bfc6d0b19d56865ed1e175860 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 26 Jun 2025 11:42:53 +0530
Subject: [PATCH v5 2/8] Refactor: pg_waldump: Separate logic used to calculate
 the required read size.

This refactoring prepares the codebase for an upcoming patch that will
support reading WAL from tar files. The logic for calculating the
required read size has been updated to handle both normal WAL files
and WAL files located inside a tar archive.
---
 src/bin/pg_waldump/pg_waldump.c | 39 ++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index a49b2fd96c7..8d0cd9e7156 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -326,6 +326,29 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/* Returns the size in bytes of the data to be read. */
+static inline int
+required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
+				  int reqLen)
+{
+	int			count = XLOG_BLCKSZ;
+
+	if (private->endptr != InvalidXLogRecPtr)
+	{
+		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
+			count = XLOG_BLCKSZ;
+		else if (targetPagePtr + reqLen <= private->endptr)
+			count = private->endptr - targetPagePtr;
+		else
+		{
+			private->endptr_reached = true;
+			return -1;
+		}
+	}
+
+	return count;
+}
+
 /* pg_waldump's XLogReaderRoutine->segment_open callback */
 static void
 WALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
@@ -383,21 +406,11 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = XLOG_BLCKSZ;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
-	if (private->endptr != InvalidXLogRecPtr)
-	{
-		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
-			count = XLOG_BLCKSZ;
-		else if (targetPagePtr + reqLen <= private->endptr)
-			count = private->endptr - targetPagePtr;
-		else
-		{
-			private->endptr_reached = true;
-			return -1;
-		}
-	}
+	if (private->endptr_reached)
+		return -1;
 
 	if (!WALRead(state, readBuff, targetPagePtr, count, private->timeline,
 				 &errinfo))
-- 
2.47.1

From fdf23c243bc21cefd062d2b4960460722805bbee Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 30 Jul 2025 12:43:30 +0530
Subject: [PATCH v5 3/8] Refactor: pg_waldump: Restructure TAP tests.

Restructured some tests to run inside a loop, facilitating their
re-execution for decoding WAL from tar archives.
---
 src/bin/pg_waldump/t/001_basic.pl | 123 ++++++++++++++++--------------
 1 file changed, 67 insertions(+), 56 deletions(-)

diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index f26d75e01cf..1b712e8d74d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -198,28 +198,6 @@ command_like(
 	],
 	qr/./,
 	'runs with start and end segment specified');
-command_fails_like(
-	[ 'pg_waldump', '--path' => $node->data_dir ],
-	qr/error: no start WAL location given/,
-	'path option requires start location');
-command_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-		'--end' => $end_lsn,
-	],
-	qr/./,
-	'runs with path option and start and end locations');
-command_fails_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-	],
-	qr/error: error in WAL record at/,
-	'falling off the end of the WAL results in an error');
-
 command_like(
 	[
 		'pg_waldump', '--quiet',
@@ -227,15 +205,6 @@ command_like(
 	],
 	qr/^$/,
 	'no output with --quiet option');
-command_fails_like(
-	[
-		'pg_waldump', '--quiet',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn
-	],
-	qr/error: error in WAL record at/,
-	'errors are shown with --quiet');
-
 
 # Test for: Display a message that we're skipping data if `from`
 # wasn't a pointer to the start of a record.
@@ -272,7 +241,6 @@ sub test_pg_waldump
 
 	my $result = IPC::Run::run [
 		'pg_waldump',
-		'--path' => $node->data_dir,
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
 		@opts
@@ -288,38 +256,81 @@ sub test_pg_waldump
 
 my @lines;
 
-@lines = test_pg_waldump;
-is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
+my @scenario = (
+	{
+		'path' => $node->data_dir
+	});
 
-@lines = test_pg_waldump('--limit' => 6);
-is(@lines, 6, 'limit option observed');
+for my $scenario (@scenario)
+{
+	my $path = $scenario->{'path'};
 
-@lines = test_pg_waldump('--fullpage');
-is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
+	SKIP:
+	{
+		command_fails_like(
+			[ 'pg_waldump', '--path' => $path ],
+			qr/error: no start WAL location given/,
+			'path option requires start location');
+		command_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+				'--end' => $end_lsn,
+			],
+			qr/./,
+			'runs with path option and start and end locations');
+		command_fails_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+			],
+			qr/error: error in WAL record at/,
+			'falling off the end of the WAL results in an error');
 
-@lines = test_pg_waldump('--stats');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		command_fails_like(
+			[
+				'pg_waldump', '--quiet',
+				'--path' => $path,
+				'--start' => $start_lsn
+			],
+			qr/error: error in WAL record at/,
+			'errors are shown with --quiet');
 
-@lines = test_pg_waldump('--stats=record');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		@lines = test_pg_waldump('--path' => $path);
+		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-@lines = test_pg_waldump('--rmgr' => 'Btree');
-is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		is(@lines, 6, 'limit option observed');
 
-@lines = test_pg_waldump('--fork' => 'init');
-is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
-is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
-	0, 'only lines for selected relation');
+		@lines = test_pg_waldump('--path' => $path, '--stats');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
-	'--block' => 1);
-is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
+		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+
+		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
+		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
+			0, 'only lines for selected relation');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
+			'--block' => 1);
+		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+	}
+}
 
 done_testing();
-- 
2.47.1

From 787fc3c94431dedcc0d37d3d6d9329b62e4d00c5 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 5 Nov 2025 15:40:36 +0530
Subject: [PATCH v5 4/8] pg_waldump: Add support for archived WAL decoding.

pg_waldump can now accept the path to a tar archive containing WAL
files and decode them. This feature was added primarily for
pg_verifybackup, which previously disabled WAL parsing for
tar-formatted backups.

Note that this patch requires that the WAL files within the archive be
in sequential order; an error will be reported otherwise. The next
patch is planned to remove this restriction.
---
 doc/src/sgml/ref/pg_waldump.sgml     |   8 +-
 src/bin/pg_waldump/Makefile          |   7 +-
 src/bin/pg_waldump/archive_waldump.c | 577 +++++++++++++++++++++++++++
 src/bin/pg_waldump/meson.build       |   4 +-
 src/bin/pg_waldump/pg_waldump.c      | 222 ++++++++---
 src/bin/pg_waldump/pg_waldump.h      |  36 +-
 src/bin/pg_waldump/t/001_basic.pl    |  84 +++-
 src/tools/pgindent/typedefs.list     |   3 +
 8 files changed, 863 insertions(+), 78 deletions(-)
 create mode 100644 src/bin/pg_waldump/archive_waldump.c

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index ce23add5577..d004bb0f67e 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -141,13 +141,17 @@ PostgreSQL documentation
       <term><option>--path=<replaceable>path</replaceable></option></term>
       <listitem>
        <para>
-        Specifies a directory to search for WAL segment files or a
-        directory with a <literal>pg_wal</literal> subdirectory that
+        Specifies a tar archive or a directory to search for WAL segment files
+        or a directory with a <literal>pg_wal</literal> subdirectory that
         contains such files.  The default is to search in the current
         directory, the <literal>pg_wal</literal> subdirectory of the
         current directory, and the <literal>pg_wal</literal> subdirectory
         of <envar>PGDATA</envar>.
        </para>
+       <para>
+        If a tar archive is provided, its WAL segment files must be in
+        sequential order; otherwise, an error will be reported.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index 4c1ee649501..05ac5763a57 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -3,6 +3,9 @@
 PGFILEDESC = "pg_waldump - decode and display WAL"
 PGAPPICON=win32
 
+# make these available to TAP test scripts
+export TAR
+
 subdir = src/bin/pg_waldump
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
@@ -12,11 +15,13 @@ OBJS = \
 	$(WIN32RES) \
 	compat.o \
 	pg_waldump.o \
+	archive_waldump.o \
 	rmgrdesc.o \
 	xlogreader.o \
 	xlogstats.o
 
-override CPPFLAGS := -DFRONTEND $(CPPFLAGS)
+override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
new file mode 100644
index 00000000000..e619e29d5d4
--- /dev/null
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -0,0 +1,577 @@
+/*-------------------------------------------------------------------------
+ *
+ * archive_waldump.c
+ *		A generic facility for reading WAL data from tar archives via archive
+ *		streamer.
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/bin/pg_waldump/archive_waldump.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <unistd.h>
+
+#include "access/xlog_internal.h"
+#include "common/hashfn.h"
+#include "common/logging.h"
+#include "fe_utils/simple_list.h"
+#include "pg_waldump.h"
+
+/*
+ * How many bytes should we try to read from a file at once?
+ */
+#define READ_CHUNK_SIZE				(128 * 1024)
+
+/* Structure for storing the WAL segment data from the archive */
+typedef struct ArchivedWALEntry
+{
+	uint32		status;			/* hash status */
+	XLogSegNo	segno;			/* hash key: WAL segment number */
+	TimeLineID	timeline;		/* timeline of this wal file */
+
+	StringInfoData buf;
+	bool		tmpseg_exists;	/* spill file exists? */
+
+	int			total_read;		/* total read of this WAL segment, including
+								 * buffered and temporarily written data */
+} ArchivedWALEntry;
+
+#define SH_PREFIX				ArchivedWAL
+#define SH_ELEMENT_TYPE			ArchivedWALEntry
+#define SH_KEY_TYPE				XLogSegNo
+#define SH_KEY					segno
+#define SH_HASH_KEY(tb, key)	murmurhash64((uint64) key)
+#define SH_EQUAL(tb, a, b)		(a == b)
+#define SH_GET_HASH(tb, a)		a->hash
+#define SH_SCOPE				static inline
+#define SH_RAW_ALLOCATOR		pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static ArchivedWAL_hash *ArchivedWAL_HTAB = NULL;
+
+typedef struct astreamer_waldump
+{
+	astreamer	base;
+	XLogDumpPrivate *privateInfo;
+} astreamer_waldump;
+
+static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
+static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
+											   XLogDumpPrivate *privateInfo);
+
+static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
+static void astreamer_waldump_content(astreamer *streamer,
+									  astreamer_member *member,
+									  const char *data, int len,
+									  astreamer_archive_context context);
+static void astreamer_waldump_finalize(astreamer *streamer);
+static void astreamer_waldump_free(astreamer *streamer);
+
+static bool member_is_wal_file(astreamer_waldump *mystreamer,
+							   astreamer_member *member,
+							   XLogSegNo *curSegNo,
+							   TimeLineID *curTimeline);
+
+static const astreamer_ops astreamer_waldump_ops = {
+	.content = astreamer_waldump_content,
+	.finalize = astreamer_waldump_finalize,
+	.free = astreamer_waldump_free
+};
+
+/*
+ * Returns true if the given file is a tar archive and outputs its compression
+ * algorithm.
+ */
+bool
+is_archive_file(const char *fname, pg_compress_algorithm *compression)
+{
+	int			fname_len = strlen(fname);
+	pg_compress_algorithm compress_algo;
+
+	/* Now, check the compression type of the tar */
+	if (fname_len > 4 &&
+		strcmp(fname + fname_len - 4, ".tar") == 0)
+		compress_algo = PG_COMPRESSION_NONE;
+	else if (fname_len > 4 &&
+			 strcmp(fname + fname_len - 4, ".tgz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 7 &&
+			 strcmp(fname + fname_len - 7, ".tar.gz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.lz4") == 0)
+		compress_algo = PG_COMPRESSION_LZ4;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.zst") == 0)
+		compress_algo = PG_COMPRESSION_ZSTD;
+	else
+		return false;
+
+	*compression = compress_algo;
+
+	return true;
+}
+
+/*
+ * Initializes the tar archive reader to read WAL files from the archive,
+ * creates a hash table to store them, performs quick existence checks for WAL
+ * entries in the archive and retrieves the WAL segment size, and sets up
+ * filtering criteria for relevant entries.
+ */
+void
+init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
+					pg_compress_algorithm compression)
+{
+	int			fd;
+	astreamer  *streamer;
+	ArchivedWALEntry *entry = NULL;
+	XLogLongPageHeader longhdr;
+
+	/* Open tar archive and store its file descriptor */
+	fd = open_file_in_directory(waldir, privateInfo->archive_name);
+
+	if (fd < 0)
+		pg_fatal("could not open file \"%s\"", privateInfo->archive_name);
+
+	privateInfo->archive_fd = fd;
+
+	streamer = astreamer_waldump_new(privateInfo);
+
+	/* Before that we must parse the tar archive. */
+	streamer = astreamer_tar_parser_new(streamer);
+
+	/* Before that we must decompress, if archive is compressed. */
+	if (compression == PG_COMPRESSION_GZIP)
+		streamer = astreamer_gzip_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_LZ4)
+		streamer = astreamer_lz4_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_ZSTD)
+		streamer = astreamer_zstd_decompressor_new(streamer);
+
+	privateInfo->archive_streamer = streamer;
+
+	/* Hash table storing WAL entries read from the archive */
+	ArchivedWAL_HTAB = ArchivedWAL_create(16, NULL);
+
+	/*
+	 * Verify that the archive contains valid WAL files and fetch WAL segment
+	 * size
+	 */
+	while (entry == NULL || entry->buf.len < XLOG_BLCKSZ)
+	{
+		if (read_archive_file(privateInfo, XLOG_BLCKSZ) == 0)
+			pg_fatal("could not find WAL in \"%s\" archive",
+					 privateInfo->archive_name);
+
+		entry = privateInfo->cur_wal;
+	}
+
+	/* Set WalSegSz if WAL data is successfully read */
+	longhdr = (XLogLongPageHeader) entry->buf.data;
+
+	WalSegSz = longhdr->xlp_seg_size;
+
+	if (!IsValidWalSegSize(WalSegSz))
+	{
+		pg_log_error(ngettext("invalid WAL segment size in WAL file from archive \"%s\" (%d byte)",
+							  "invalid WAL segment size in WAL file from archive \"%s\" (%d bytes)",
+							  WalSegSz),
+					 privateInfo->archive_name, WalSegSz);
+		pg_log_error_detail("The WAL segment size must be a power of two between 1 MB and 1 GB.");
+		exit(1);
+	}
+
+	/*
+	 * With the WAL segment size available, we can now initialize the
+	 * dependent start and end segment numbers.
+	 */
+	XLByteToSeg(privateInfo->startptr, privateInfo->startSegNo, WalSegSz);
+	XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+}
+
+/*
+ * Release the archive streamer chain and close the archive file.
+ */
+void
+free_archive_reader(XLogDumpPrivate *privateInfo)
+{
+	/*
+	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
+	 * flush any remaining buffered data or to ensure the end of the tar
+	 * archive is reached. However, when decoding a WAL file, once we hit the
+	 * end LSN, any remaining WAL data in the buffer or the tar archive's
+	 * unreached end can be safely ignored.
+	 */
+	astreamer_free(privateInfo->archive_streamer);
+
+	/* Close the file. */
+	if (close(privateInfo->archive_fd) != 0)
+		pg_log_error("could not close file \"%s\": %m",
+					 privateInfo->archive_name);
+}
+
+/*
+ * Copies WAL data from astreamer to readBuff; if unavailable, fetches more
+ * from the tar archive via astreamer.
+ */
+int
+read_archive_wal_page(XLogDumpPrivate *privateInfo, XLogRecPtr targetPagePtr,
+					  Size count, char *readBuff)
+{
+	char	   *p = readBuff;
+	Size		nbytes = count;
+	XLogRecPtr	recptr = targetPagePtr;
+	XLogSegNo	segno;
+	ArchivedWALEntry *entry;
+
+	XLByteToSeg(targetPagePtr, segno, WalSegSz);
+	entry = get_archive_wal_entry(segno, privateInfo);
+
+	while (nbytes > 0)
+	{
+		char	   *buf = entry->buf.data;
+		int			len = entry->buf.len;
+
+		/* WAL record range that the buffer contains */
+		XLogRecPtr	endPtr;
+		XLogRecPtr	startPtr;
+
+		XLogSegNoOffsetToRecPtr(entry->segno, entry->total_read,
+								WalSegSz, endPtr);
+		startPtr = endPtr - len;
+
+		Assert((endPtr - startPtr) == len);
+
+		/*
+		 * pg_waldump never ask the same WAL bytes more than once, so if we're
+		 * now being asked for data beyond the end of what we've already read,
+		 * that means none of the data we currently have in the buffer will
+		 * ever be consulted again. So, we can discard the existing buffer
+		 * contents and start over.
+		 */
+		if (recptr >= endPtr)
+		{
+			len = 0;
+
+			/* Discard the buffered data */
+			resetStringInfo(&entry->buf);
+		}
+
+		if (len > 0 && recptr > startPtr)
+		{
+			int			skipBytes = 0;
+
+			/*
+			 * The required offset is not at the start of the buffer, so skip
+			 * bytes until reaching the desired offset of the target page.
+			 */
+			skipBytes = recptr - startPtr;
+
+			buf += skipBytes;
+			len -= skipBytes;
+		}
+
+		if (len > 0)
+		{
+			int			readBytes = len >= nbytes ? nbytes : len;
+
+			/* Ensure reading correct WAL record */
+			Assert(recptr >= startPtr && recptr < endPtr);
+
+			memcpy(p, buf, readBytes);
+
+			/* Update state for read */
+			nbytes -= readBytes;
+			p += readBytes;
+			recptr += readBytes;
+		}
+		else
+		{
+			/*
+			 * Fetch more data; raise an error if it's not the current segment
+			 * being read by the archive streamer or if reading of the
+			 * archived file has finished.
+			 */
+			if (privateInfo->cur_wal != entry ||
+				read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+			{
+				char		fname[MAXFNAMELEN];
+
+				XLogFileName(fname, privateInfo->timeline, entry->segno,
+							 WalSegSz);
+				pg_fatal("could not read file \"%s\" from archive \"%s\": read %lld of %lld",
+						 fname, privateInfo->archive_name,
+						 (long long int) count - nbytes,
+						 (long long int) nbytes);
+			}
+		}
+	}
+
+	/*
+	 * Should have either have successfully read all the requested bytes or
+	 * reported a failure before this point.
+	 */
+	Assert(nbytes == 0);
+
+	/*
+	 * NB: We return the fixed value provided as input. Although we could
+	 * return a boolean since we either successfully read the WAL page or
+	 * raise an error, but the caller expects this value to be returned. The
+	 * routine that reads WAL pages from the physical WAL file follows the
+	 * same convention.
+	 */
+	return count;
+}
+
+/*
+ * Reads the archive file and passes it to the archive streamer for
+ * decompression.
+ */
+static int
+read_archive_file(XLogDumpPrivate *privateInfo, Size count)
+{
+	int			rc;
+	char	   *buffer;
+
+	buffer = pg_malloc(READ_CHUNK_SIZE * sizeof(uint8));
+
+	rc = read(privateInfo->archive_fd, buffer, count);
+	if (rc < 0)
+		pg_fatal("could not read file \"%s\": %m",
+				 privateInfo->archive_name);
+
+	/*
+	 * Decompress (if required), and then parse the previously read contents
+	 * of the tar file.
+	 */
+	if (rc > 0)
+		astreamer_content(privateInfo->archive_streamer, NULL,
+						  buffer, rc, ASTREAMER_UNKNOWN);
+	pg_free(buffer);
+
+	return rc;
+}
+
+/*
+ * Returns the archived WAL entry from the hash table if it exists. Otherwise,
+ * it invokes the routine to read the archived file and retrieve the entry if
+ * it is not already in hash table.
+ */
+static ArchivedWALEntry *
+get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
+{
+	ArchivedWALEntry *entry = NULL;
+	char		fname[MAXFNAMELEN];
+
+	/* Search hash table */
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry != NULL)
+		return entry;
+
+	/* Needed WAL yet to be decoded from archive, do the same */
+	while (1)
+	{
+		entry = privateInfo->cur_wal;
+
+		/* Fetch more data */
+		if (entry == NULL || entry->buf.len == 0)
+		{
+			if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+				break;			/* archive file ended */
+		}
+
+		/*
+		 * Either, here for the first time, or the archived streamer is
+		 * reading a non-WAL file or an irrelevant WAL file.
+		 */
+		if (entry == NULL)
+			continue;
+
+		/* Found the required entry */
+		if (entry->segno == segno)
+			return entry;
+
+		/*
+		 * Ignore if the timeline is different or the current segment is not
+		 * the desired one.
+		 */
+		if (privateInfo->timeline != entry->timeline ||
+			privateInfo->startSegNo > entry->segno ||
+			privateInfo->endSegNo < entry->segno)
+		{
+			privateInfo->cur_wal = NULL;
+			continue;
+		}
+
+		/* WAL segments must be archived in order */
+		pg_log_error("WAL files are not archived in sequential order");
+		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
+							segno, entry->segno);
+		exit(1);
+	}
+
+	/* Requested WAL segment not found */
+	XLogFileName(fname, privateInfo->timeline, segno, WalSegSz);
+	pg_fatal("could not find file \"%s\" in archive", fname);
+}
+
+/*
+ * Create an astreamer that can read WAL from tar file.
+ */
+static astreamer *
+astreamer_waldump_new(XLogDumpPrivate *privateInfo)
+{
+	astreamer_waldump *streamer;
+
+	streamer = palloc0(sizeof(astreamer_waldump));
+	*((const astreamer_ops **) &streamer->base.bbs_ops) =
+		&astreamer_waldump_ops;
+
+	streamer->privateInfo = privateInfo;
+
+	return &streamer->base;
+}
+
+/*
+ * Main entry point of the archive streamer for reading WAL data from a tar
+ * file. If a member is identified as a valid WAL file, a hash entry is created
+ * for it, and its contents are copied into that entry's buffer, making them
+ * accessible to the decoding routine.
+ */
+static void
+astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
+						  const char *data, int len,
+						  astreamer_archive_context context)
+{
+	astreamer_waldump *mystreamer = (astreamer_waldump *) streamer;
+	XLogDumpPrivate *privateInfo = mystreamer->privateInfo;
+
+	Assert(context != ASTREAMER_UNKNOWN);
+
+	switch (context)
+	{
+		case ASTREAMER_MEMBER_HEADER:
+			{
+				XLogSegNo	segno;
+				TimeLineID	timeline;
+				ArchivedWALEntry *entry;
+				bool		found;
+
+				pg_log_debug("pg_waldump: reading \"%s\"", member->pathname);
+
+				if (!member_is_wal_file(mystreamer, member,
+										&segno, &timeline))
+					break;
+
+				entry = ArchivedWAL_insert(ArchivedWAL_HTAB, segno, &found);
+
+				/*
+				 * Shouldn't happen, but if it does, simply ignore the
+				 * duplicate WAL file.
+				 */
+				if (found)
+				{
+					pg_log_warning("ignoring duplicate WAL file found in archive: \"%s\"",
+								   member->pathname);
+					break;
+				}
+
+				initStringInfo(&entry->buf);
+				entry->timeline = timeline;
+				entry->total_read = 0;
+
+				privateInfo->cur_wal = entry;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_CONTENTS:
+			if (privateInfo->cur_wal)
+			{
+				appendBinaryStringInfo(&privateInfo->cur_wal->buf, data, len);
+				privateInfo->cur_wal->total_read += len;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_TRAILER:
+			privateInfo->cur_wal = NULL;
+			break;
+
+		case ASTREAMER_ARCHIVE_TRAILER:
+			break;
+
+		default:
+			/* Shouldn't happen. */
+			pg_fatal("unexpected state while parsing tar file");
+	}
+}
+
+/*
+ * End-of-stream processing for a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_finalize(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+}
+
+/*
+ * Free memory associated with a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_free(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+	pfree(streamer);
+}
+
+/*
+ * Returns true if the archive member name matches the WAL naming format. If
+ * successful, it also outputs the WAL segment number, and timeline.
+ */
+static bool
+member_is_wal_file(astreamer_waldump *mystreamer, astreamer_member *member,
+				   XLogSegNo *curSegNo, TimeLineID *curTimeline)
+{
+	int			pathlen;
+	XLogSegNo	segNo;
+	TimeLineID	timeline;
+	char	   *fname;
+
+	/* We are only interested in normal files. */
+	if (member->is_directory || member->is_link)
+		return false;
+
+	pathlen = strlen(member->pathname);
+	if (pathlen < XLOG_FNAME_LEN)
+		return false;
+
+	/* WAL file could be with full path */
+	fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+	if (!IsXLogFileName(fname))
+		return false;
+
+	/*
+	 * XXX: On some systems (e.g., OpenBSD), the tar utility includes
+	 * PaxHeaders when creating an archive. These are special entries that
+	 * store extended metadata for the file entry immediately following them,
+	 * and they share the exact same name as that file.
+	 */
+	if (strstr(member->pathname, "PaxHeaders."))
+		return false;
+
+	/* Parse position from file */
+	XLogFromFileName(fname, &timeline, &segNo, WalSegSz);
+
+	*curSegNo = segNo;
+	*curTimeline = timeline;
+
+	return true;
+}
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 937e0d68841..da00746587c 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -3,6 +3,7 @@
 pg_waldump_sources = files(
   'compat.c',
   'pg_waldump.c',
+  'archive_waldump.c',
   'rmgrdesc.c',
 )
 
@@ -18,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, lz4, zstd],
+  dependencies: [frontend_code, lz4, zstd, libpq],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
@@ -29,6 +30,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'TAR': tar.found() ? tar.full_path() : ''},
     'tests': [
       't/001_basic.pl',
       't/002_save_fullpage.pl',
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 8d0cd9e7156..8a838f16ba2 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -177,7 +177,7 @@ split_path(const char *path, char **dir, char **fname)
  *
  * return a read only fd
  */
-static int
+int
 open_file_in_directory(const char *directory, const char *fname)
 {
 	int			fd = -1;
@@ -436,6 +436,44 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 	return count;
 }
 
+/*
+ * pg_waldump's XLogReaderRoutine->segment_open callback to support dumping WAL
+ * files from tar archives.
+ */
+static void
+TarWALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
+					  TimeLineID *tli_p)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->segment_close callback.
+ */
+static void
+TarWALDumpCloseSegment(XLogReaderState *state)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->page_read callback to support dumping WAL
+ * files from tar archives.
+ */
+static int
+TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				   XLogRecPtr targetPtr, char *readBuff)
+{
+	XLogDumpPrivate *private = state->private_data;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
+
+	if (private->endptr_reached)
+		return -1;
+
+	/* Read the WAL page from the archive streamer */
+	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
+}
+
 /*
  * Boolean to return whether the given WAL record matches a specific relation
  * and optionally block.
@@ -773,8 +811,8 @@ usage(void)
 	printf(_("  -F, --fork=FORK        only show records that modify blocks in fork FORK;\n"
 			 "                         valid names are main, fsm, vm, init\n"));
 	printf(_("  -n, --limit=N          number of records to display\n"));
-	printf(_("  -p, --path=PATH        directory in which to find WAL segment files or a\n"
-			 "                         directory with a ./pg_wal that contains such files\n"
+	printf(_("  -p, --path=PATH        tar archive or a directory in which to find WAL segment files or\n"
+			 "                         a directory with a ./pg_wal that contains such files\n"
 			 "                         (default: current directory, ./pg_wal, $PGDATA/pg_wal)\n"));
 	printf(_("  -q, --quiet            do not print any output, except for errors\n"));
 	printf(_("  -r, --rmgr=RMGR        only show records generated by resource manager RMGR;\n"
@@ -806,7 +844,10 @@ main(int argc, char **argv)
 	XLogRecord *record;
 	XLogRecPtr	first_record;
 	char	   *waldir = NULL;
+	char	   *walpath = NULL;
 	char	   *errormsg;
+	bool		is_archive = false;
+	pg_compress_algorithm compression;
 
 	static struct option long_options[] = {
 		{"bkp-details", no_argument, NULL, 'b'},
@@ -938,7 +979,7 @@ main(int argc, char **argv)
 				}
 				break;
 			case 'p':
-				waldir = pg_strdup(optarg);
+				walpath = pg_strdup(optarg);
 				break;
 			case 'q':
 				config.quiet = true;
@@ -1102,10 +1143,27 @@ main(int argc, char **argv)
 		goto bad_argument;
 	}
 
-	if (waldir != NULL)
+	if (walpath != NULL)
 	{
+		/* validate path points to tar archive */
+		if (is_archive_file(walpath, &compression))
+		{
+			char	   *fname = NULL;
+
+			split_path(walpath, &waldir, &fname);
+
+			/*
+			 * A NULL WAL directory indicates that the archive file is located
+			 * in the current working directory of the pg_waldump execution
+			 */
+			if (waldir == NULL)
+				waldir = pg_strdup(".");
+
+			private.archive_name = fname;
+			is_archive = true;
+		}
 		/* validate path points to directory */
-		if (!verify_directory(waldir))
+		else if (!verify_directory(walpath))
 		{
 			pg_log_error("could not open directory \"%s\": %m", waldir);
 			goto bad_argument;
@@ -1123,46 +1181,36 @@ main(int argc, char **argv)
 		int			fd;
 		XLogSegNo	segno;
 
+		/*
+		 * If a tar archive is passed using the --path option, all other
+		 * arguments become unnecessary.
+		 */
+		if (is_archive)
+		{
+			pg_log_error("unnecessary command-line arguments specified with tar archive (first is \"%s\")",
+						 argv[optind]);
+			goto bad_argument;
+		}
+
 		split_path(argv[optind], &directory, &fname);
 
-		if (waldir == NULL && directory != NULL)
+		if (walpath == NULL && directory != NULL)
 		{
-			waldir = directory;
+			walpath = directory;
 
-			if (!verify_directory(waldir))
+			if (!verify_directory(walpath))
 				pg_fatal("could not open directory \"%s\": %m", waldir);
 		}
 
-		waldir = identify_target_directory(waldir, fname);
-		fd = open_file_in_directory(waldir, fname);
-		if (fd < 0)
-			pg_fatal("could not open file \"%s\"", fname);
-		close(fd);
-
-		/* parse position from file */
-		XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
-
-		if (XLogRecPtrIsInvalid(private.startptr))
-			XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
-		else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+		if (fname != NULL && is_archive_file(fname, &compression))
 		{
-			pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.startptr),
-						 fname);
-			goto bad_argument;
+			waldir = walpath ? pg_strdup(walpath) : pg_strdup(".");
+			private.archive_name = fname;
+			is_archive = true;
 		}
-
-		/* no second file specified, set end position */
-		if (!(optind + 1 < argc) && XLogRecPtrIsInvalid(private.endptr))
-			XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
-
-		/* parse ENDSEG if passed */
-		if (optind + 1 < argc)
+		else
 		{
-			XLogSegNo	endsegno;
-
-			/* ignore directory, already have that */
-			split_path(argv[optind + 1], &directory, &fname);
+			waldir = identify_target_directory(walpath, fname);
 
 			fd = open_file_in_directory(waldir, fname);
 			if (fd < 0)
@@ -1170,32 +1218,63 @@ main(int argc, char **argv)
 			close(fd);
 
 			/* parse position from file */
-			XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+			XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
 
-			if (endsegno < segno)
-				pg_fatal("ENDSEG %s is before STARTSEG %s",
-						 argv[optind + 1], argv[optind]);
+			if (XLogRecPtrIsInvalid(private.startptr))
+				XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
+			else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+			{
+				pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.startptr),
+							 fname);
+				goto bad_argument;
+			}
 
-			if (XLogRecPtrIsInvalid(private.endptr))
-				XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
-										private.endptr);
+			/* no second file specified, set end position */
+			if (!(optind + 1 < argc) && XLogRecPtrIsInvalid(private.endptr))
+				XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
 
-			/* set segno to endsegno for check of --end */
-			segno = endsegno;
-		}
+			/* parse ENDSEG if passed */
+			if (optind + 1 < argc)
+			{
+				XLogSegNo	endsegno;
 
+				/* ignore directory, already have that */
+				split_path(argv[optind + 1], &directory, &fname);
 
-		if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
-			private.endptr != (segno + 1) * WalSegSz)
-		{
-			pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.endptr),
-						 argv[argc - 1]);
-			goto bad_argument;
+				fd = open_file_in_directory(waldir, fname);
+				if (fd < 0)
+					pg_fatal("could not open file \"%s\"", fname);
+				close(fd);
+
+				/* parse position from file */
+				XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+
+				if (endsegno < segno)
+					pg_fatal("ENDSEG %s is before STARTSEG %s",
+							 argv[optind + 1], argv[optind]);
+
+				if (XLogRecPtrIsInvalid(private.endptr))
+					XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
+											private.endptr);
+
+				/* set segno to endsegno for check of --end */
+				segno = endsegno;
+			}
+
+
+			if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
+				private.endptr != (segno + 1) * WalSegSz)
+			{
+				pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.endptr),
+							 argv[argc - 1]);
+				goto bad_argument;
+			}
 		}
 	}
-	else
-		waldir = identify_target_directory(waldir, NULL);
+	else if (!is_archive)
+		waldir = identify_target_directory(walpath, NULL);
 
 	/* we don't know what to print */
 	if (XLogRecPtrIsInvalid(private.startptr))
@@ -1207,12 +1286,30 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
-	xlogreader_state =
-		XLogReaderAllocate(WalSegSz, waldir,
-						   XL_ROUTINE(.page_read = WALDumpReadPage,
-									  .segment_open = WALDumpOpenSegment,
-									  .segment_close = WALDumpCloseSegment),
-						   &private);
+	if (is_archive)
+	{
+		/* Set up for reading tar file */
+		init_archive_reader(&private, waldir, compression);
+
+		/* Routine to decode WAL files in tar archive */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = TarWALDumpReadPage,
+										  .segment_open = TarWALDumpOpenSegment,
+										  .segment_close = TarWALDumpCloseSegment),
+							   &private);
+	}
+	else
+	{
+		/* Routine to decode WAL files */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = WALDumpReadPage,
+										  .segment_open = WALDumpOpenSegment,
+										  .segment_close = WALDumpCloseSegment),
+							   &private);
+	}
+
 	if (!xlogreader_state)
 		pg_fatal("out of memory while allocating a WAL reading processor");
 
@@ -1321,6 +1418,9 @@ main(int argc, char **argv)
 
 	XLogReaderFree(xlogreader_state);
 
+	if (is_archive)
+		free_archive_reader(&private);
+
 	return EXIT_SUCCESS;
 
 bad_argument:
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 9e62b64ead5..54758c3548a 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -12,9 +12,13 @@
 #define PG_WALDUMP_H
 
 #include "access/xlogdefs.h"
+#include "fe_utils/astreamer.h"
 
 extern int	WalSegSz;
 
+/* Forward declaration */
+struct ArchivedWALEntry;
+
 /* Contains the necessary information to drive WAL decoding */
 typedef struct XLogDumpPrivate
 {
@@ -22,6 +26,36 @@ typedef struct XLogDumpPrivate
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	bool		endptr_reached;
+
+	/* Fields required to read WAL from archive */
+	char	   *archive_name;	/* Tar archive name */
+	int			archive_fd;		/* File descriptor for the open tar file */
+
+	astreamer  *archive_streamer;
+
+	/* What the archive streamer is currently reading */
+	struct ArchivedWALEntry *cur_wal;
+
+	/*
+	 * Although these values can be easily derived from startptr and endptr,
+	 * doing so repeatedly for each archived member would be inefficient, as
+	 * it would involve recalculating and filtering out irrelevant WAL
+	 * segments.
+	 */
+	XLogSegNo	startSegNo;
+	XLogSegNo	endSegNo;
 } XLogDumpPrivate;
 
-#endif		/* end of PG_WALDUMP_H */
+extern int	open_file_in_directory(const char *directory, const char *fname);
+
+extern bool is_archive_file(const char *fname,
+							pg_compress_algorithm *compression);
+extern void init_archive_reader(XLogDumpPrivate *privateInfo,
+								const char *waldir,
+								pg_compress_algorithm compression);
+extern void free_archive_reader(XLogDumpPrivate *privateInfo);
+extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
+								  XLogRecPtr targetPagePtr,
+								  Size count, char *readBuff);
+
+#endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 1b712e8d74d..443126a9ce6 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -3,10 +3,13 @@
 
 use strict;
 use warnings FATAL => 'all';
+use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
 
+my $tar = $ENV{TAR};
+
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
 program_options_handling_ok('pg_waldump');
@@ -235,7 +238,7 @@ command_like(
 sub test_pg_waldump
 {
 	local $Test::Builder::Level = $Test::Builder::Level + 1;
-	my @opts = @_;
+	my ($path, @opts) = @_;
 
 	my ($stdout, $stderr);
 
@@ -243,6 +246,7 @@ sub test_pg_waldump
 		'pg_waldump',
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
+		'--path' => $path,
 		@opts
 	  ],
 	  '>' => \$stdout,
@@ -254,11 +258,50 @@ sub test_pg_waldump
 	return @lines;
 }
 
-my @lines;
+# Create a tar archive, sorting the file order
+sub generate_archive
+{
+	my ($archive, $directory, $compression_flags) = @_;
+
+	my @files;
+	opendir my $dh, $directory or die "opendir: $!";
+	while (my $entry = readdir $dh) {
+		# Skip '.' and '..'
+		next if $entry eq '.' || $entry eq '..';
+		push @files, $entry;
+	}
+	closedir $dh;
+
+	@files = sort @files;
+
+	# move into the WAL directory before archiving files
+	my $cwd = getcwd;
+	chdir($directory) || die "chdir: $!";
+	command_ok([$tar, $compression_flags, $archive, @files]);
+	chdir($cwd) || die "chdir: $!";
+}
+
+my $tmp_dir = PostgreSQL::Test::Utils::tempdir_short();
 
 my @scenario = (
 	{
-		'path' => $node->data_dir
+		'path' => $node->data_dir,
+		'is_archive' => 0,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar",
+		'compression_method' => 'none',
+		'compression_flags' => '-cf',
+		'is_archive' => 1,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar.gz",
+		'compression_method' => 'gzip',
+		'compression_flags' => '-czf',
+		'is_archive' => 1,
+		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
 	});
 
 for my $scenario (@scenario)
@@ -267,6 +310,19 @@ for my $scenario (@scenario)
 
 	SKIP:
 	{
+		skip "tar command is not available", 3
+		  if !defined $tar;
+		skip "$scenario->{'compression_method'} compression not supported by this build", 3
+		  if !$scenario->{'enabled'} && $scenario->{'is_archive'};
+
+		  # create pg_wal archive
+		  if ($scenario->{'is_archive'})
+		  {
+			  generate_archive($path,
+				  $node->data_dir . '/pg_wal',
+				  $scenario->{'compression_flags'});
+		  }
+
 		command_fails_like(
 			[ 'pg_waldump', '--path' => $path ],
 			qr/error: no start WAL location given/,
@@ -298,38 +354,42 @@ for my $scenario (@scenario)
 			qr/error: error in WAL record at/,
 			'errors are shown with --quiet');
 
-		@lines = test_pg_waldump('--path' => $path);
+		my @lines;
+		@lines = test_pg_waldump($path);
 		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		@lines = test_pg_waldump($path, '--limit' => 6);
 		is(@lines, 6, 'limit option observed');
 
-		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		@lines = test_pg_waldump($path, '--fullpage');
 		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats');
+		@lines = test_pg_waldump($path, '--stats');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		@lines = test_pg_waldump($path, '--stats=record');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		@lines = test_pg_waldump($path, '--rmgr' => 'Btree');
 		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		@lines = test_pg_waldump($path, '--fork' => 'init');
 		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
 		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
 			0, 'only lines for selected relation');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
 			'--block' => 1);
 		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+
+		# Cleanup.
+		unlink $path if $scenario->{'is_archive'};
 	}
 }
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index bb4e1b37005..de2ad42bcab 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -139,6 +139,8 @@ ArchiveOpts
 ArchiveShutdownCB
 ArchiveStartupCB
 ArchiveStreamState
+ArchivedWALEntry
+ArchivedWAL_hash
 ArchiverOutput
 ArchiverStage
 ArrayAnalyzeExtraData
@@ -3453,6 +3455,7 @@ astreamer_recovery_injector
 astreamer_tar_archiver
 astreamer_tar_parser
 astreamer_verify
+astreamer_waldump
 astreamer_zstd_frame
 auth_password_hook_typ
 autovac_table
-- 
2.47.1

From 866225e20f1389b94e25c40314b58332d7e0a6c5 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 6 Nov 2025 13:48:33 +0530
Subject: [PATCH v5 5/8] pg_waldump: Remove the restriction on the order of
 archived WAL files.

With previous patch, pg_waldump would stop decoding if WAL files were
not in the required sequence. With this patch, decoding will now
continue.  Any WAL file that is out of order will be written to a
temporary location, from which it will be read later. Once a temporary
file has been read, it will be removed.
---
 src/bin/pg_waldump/archive_waldump.c | 207 +++++++++++++++++++++++++--
 src/bin/pg_waldump/pg_waldump.c      |  41 +++++-
 src/bin/pg_waldump/pg_waldump.h      |   4 +
 src/bin/pg_waldump/t/001_basic.pl    |   3 +-
 4 files changed, 243 insertions(+), 12 deletions(-)

diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
index e619e29d5d4..4a280b58ec2 100644
--- a/src/bin/pg_waldump/archive_waldump.c
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -17,6 +17,7 @@
 #include <unistd.h>
 
 #include "access/xlog_internal.h"
+#include "common/file_perm.h"
 #include "common/hashfn.h"
 #include "common/logging.h"
 #include "fe_utils/simple_list.h"
@@ -27,6 +28,11 @@
  */
 #define READ_CHUNK_SIZE				(128 * 1024)
 
+#define TEMP_FILE_PREFIX "waldump.tmp"
+
+/* Temporary exported WAL file directory */
+static char *TmpWalSegDir = NULL;
+
 /* Structure for storing the WAL segment data from the archive */
 typedef struct ArchivedWALEntry
 {
@@ -65,6 +71,11 @@ typedef struct astreamer_waldump
 static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
 static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
 											   XLogDumpPrivate *privateInfo);
+static void setup_tmpseg_dir(const char *waldir);
+static void cleanup_tmpseg_dir_atexit(void);
+
+static FILE *prepare_tmp_write(XLogSegNo segno);
+static void perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file);
 
 static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
 static void astreamer_waldump_content(astreamer *streamer,
@@ -120,10 +131,11 @@ is_archive_file(const char *fname, pg_compress_algorithm *compression)
 }
 
 /*
- * Initializes the tar archive reader to read WAL files from the archive,
- * creates a hash table to store them, performs quick existence checks for WAL
- * entries in the archive and retrieves the WAL segment size, and sets up
- * filtering criteria for relevant entries.
+ * Initializes the tar archive reader, creates a hash table for WAL entries,
+ * checks for existing valid WAL segments in the archive file and retrieves the
+ * segment size, and sets up filters for relevant entries. It also configures a
+ * temporary directory for out-of-order WAL data and registers an exit callback
+ * to clean up temporary files.
  */
 void
 init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
@@ -194,6 +206,13 @@ init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
 	 */
 	XLByteToSeg(privateInfo->startptr, privateInfo->startSegNo, WalSegSz);
 	XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+
+	/*
+	 * Setup temporary directory to store WAL segments and set up an exit
+	 * callback to remove it upon completion.
+	 */
+	setup_tmpseg_dir(waldir);
+	atexit(cleanup_tmpseg_dir_atexit);
 }
 
 /*
@@ -362,13 +381,16 @@ read_archive_file(XLogDumpPrivate *privateInfo, Size count)
 /*
  * Returns the archived WAL entry from the hash table if it exists. Otherwise,
  * it invokes the routine to read the archived file and retrieve the entry if
- * it is not already in hash table.
+ * it is not already present in the hash table. If the archive streamer happens
+ * to be reading a WAL from archive file that is not currently needed, that WAL
+ * data is written to a temporary file.
  */
 static ArchivedWALEntry *
 get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 {
 	ArchivedWALEntry *entry = NULL;
 	char		fname[MAXFNAMELEN];
+	FILE	   *write_fp = NULL;
 
 	/* Search hash table */
 	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
@@ -411,11 +433,32 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 			continue;
 		}
 
-		/* WAL segments must be archived in order */
-		pg_log_error("WAL files are not archived in sequential order");
-		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
-							segno, entry->segno);
-		exit(1);
+		/*
+		 * Archive streamer is currently reading a file that isn't the one
+		 * asked for, but it's required for a future feature. It should be
+		 * written to a temporary location for retrieval when needed.
+		 */
+
+		/* Create a temporary file if one does not already exist */
+		if (!entry->tmpseg_exists)
+		{
+			write_fp = prepare_tmp_write(entry->segno);
+			entry->tmpseg_exists = true;
+		}
+
+		/* Flush data from the buffer to the file */
+		perform_tmp_write(entry->segno, &entry->buf, write_fp);
+		resetStringInfo(&entry->buf);
+
+		/*
+		 * The change in the current segment entry indicates that the reading
+		 * of this file has ended.
+		 */
+		if (entry != privateInfo->cur_wal && write_fp != NULL)
+		{
+			fclose(write_fp);
+			write_fp = NULL;
+		}
 	}
 
 	/* Requested WAL segment not found */
@@ -423,6 +466,150 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 	pg_fatal("could not find file \"%s\" in archive", fname);
 }
 
+/*
+ * Set up a temporary directory to temporarily store WAL segments.
+ */
+static void
+setup_tmpseg_dir(const char *waldir)
+{
+	/*
+	 * Use the directory specified by the TEMDIR environment variable. If it's
+	 * not set, use the provided WAL directory to extract WAL file
+	 * temporarily.
+	 */
+	TmpWalSegDir = getenv("TMPDIR") ?
+		pg_strdup(getenv("TMPDIR")) : pg_strdup(waldir);
+	canonicalize_path(TmpWalSegDir);
+}
+
+/*
+ * Removes the temporarily store WAL segments, if any, at exiting.
+ */
+static void
+cleanup_tmpseg_dir_atexit(void)
+{
+	ArchivedWAL_iterator it;
+	ArchivedWALEntry *entry;
+
+	ArchivedWAL_start_iterate(ArchivedWAL_HTAB, &it);
+	while ((entry = ArchivedWAL_iterate(ArchivedWAL_HTAB, &it)) != NULL)
+	{
+		if (entry->tmpseg_exists)
+		{
+			remove_tmp_walseg(entry->segno, false);
+			entry->tmpseg_exists = false;
+		}
+	}
+}
+
+/*
+ * Generate the temporary WAL file path.
+ *
+ * Note that the caller is responsible to pfree it.
+ */
+char *
+get_tmp_walseg_path(XLogSegNo segno)
+{
+	char	   *fpath = (char *) palloc(MAXPGPATH);
+
+	snprintf(fpath, MAXPGPATH, "%s/%s.%08X%08X",
+			 TmpWalSegDir,
+			 TEMP_FILE_PREFIX,
+			 (uint32) (segno / XLogSegmentsPerXLogId(WalSegSz)),
+			 (uint32) (segno % XLogSegmentsPerXLogId(WalSegSz)));
+
+	return fpath;
+}
+
+/*
+ * Routine to check whether a temporary file exists for the corresponding WAL
+ * segment number.
+ */
+bool
+tmp_walseg_exists(XLogSegNo segno)
+{
+	ArchivedWALEntry *entry;
+
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry == NULL)
+		return false;
+
+	return entry->tmpseg_exists;
+}
+
+/*
+ * Create an empty placeholder file and return its handle.
+ */
+static FILE *
+prepare_tmp_write(XLogSegNo segno)
+{
+	FILE	   *file;
+	char	   *fpath;
+
+	fpath = get_tmp_walseg_path(segno);
+
+	/* Create an empty placeholder */
+	file = fopen(fpath, PG_BINARY_W);
+	if (file == NULL)
+		pg_fatal("could not create file \"%s\": %m", fpath);
+
+#ifndef WIN32
+	if (chmod(fpath, pg_file_create_mode))
+		pg_fatal("could not set permissions on file \"%s\": %m",
+				 fpath);
+#endif
+
+	pg_log_debug("temporarily exporting file \"%s\"", fpath);
+	pfree(fpath);
+
+	return file;
+}
+
+/*
+ * Write buffer data to the given file handle.
+ */
+static void
+perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file)
+{
+	Assert(file);
+
+	errno = 0;
+	if (buf->len > 0 && fwrite(buf->data, buf->len, 1, file) != 1)
+	{
+		/*
+		 * If write didn't set errno, assume problem is no disk space
+		 */
+		if (errno == 0)
+			errno = ENOSPC;
+		pg_fatal("could not write to file \"%s\": %m",
+				 get_tmp_walseg_path(segno));
+	}
+}
+
+/*
+ * Remove temporary file
+ */
+void
+remove_tmp_walseg(XLogSegNo segno, bool update_entry)
+{
+	char	   *fpath = get_tmp_walseg_path(segno);
+
+	if (unlink(fpath) == 0)
+		pg_log_debug("removed file \"%s\"", fpath);
+	pfree(fpath);
+
+	/* Update entry if requested */
+	if (update_entry)
+	{
+		ArchivedWALEntry *entry;
+
+		entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+		Assert(entry != NULL);
+		entry->tmpseg_exists = false;
+	}
+}
+
 /*
  * Create an astreamer that can read WAL from tar file.
  */
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 8a838f16ba2..8acb7809645 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -466,11 +466,50 @@ TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 {
 	XLogDumpPrivate *private = state->private_data;
 	int			count = required_read_len(private, targetPagePtr, reqLen);
+	XLogSegNo	nextSegNo;
 
 	if (private->endptr_reached)
 		return -1;
 
-	/* Read the WAL page from the archive streamer */
+	/*
+	 * If the target page is in a different segment, first check for the WAL
+	 * segment's physical existence in the temporary directory.
+	 */
+	nextSegNo = state->seg.ws_segno;
+	if (!XLByteInSeg(targetPagePtr, nextSegNo, WalSegSz))
+	{
+		if (state->seg.ws_file >= 0)
+		{
+			close(state->seg.ws_file);
+			state->seg.ws_file = -1;
+
+			/* Remove this file, as it is no longer needed. */
+			remove_tmp_walseg(nextSegNo, true);
+		}
+
+		XLByteToSeg(targetPagePtr, nextSegNo, WalSegSz);
+		state->seg.ws_tli = private->timeline;
+		state->seg.ws_segno = nextSegNo;
+
+		/*
+		 * If the next segment exists, open it and continue reading from there
+		 */
+		if (tmp_walseg_exists(nextSegNo))
+		{
+			char	   *fpath;
+
+			fpath = get_tmp_walseg_path(nextSegNo);
+			state->seg.ws_file = open(fpath, O_RDONLY | PG_BINARY, 0);
+			pfree(fpath);
+		}
+	}
+
+	/* Continue reading from the open WAL segment, if any */
+	if (state->seg.ws_file >= 0)
+		return WALDumpReadPage(state, targetPagePtr, count, targetPtr,
+							   readBuff);
+
+	/* Otherwise, read the WAL page from the archive streamer */
 	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
 }
 
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 54758c3548a..5c1fb1e080a 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -58,4 +58,8 @@ extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
 								  XLogRecPtr targetPagePtr,
 								  Size count, char *readBuff);
 
+extern char *get_tmp_walseg_path(XLogSegNo segno);
+extern bool tmp_walseg_exists(XLogSegNo segno);
+extern void remove_tmp_walseg(XLogSegNo segno, bool update_entry);
+
 #endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 443126a9ce6..d5fa1f6d28d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -7,6 +7,7 @@ use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
+use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
 
@@ -272,7 +273,7 @@ sub generate_archive
 	}
 	closedir $dh;
 
-	@files = sort @files;
+	@files = shuffle @files;
 
 	# move into the WAL directory before archiving files
 	my $cwd = getcwd;
-- 
2.47.1

From f750f5fece87a9f642225065a540ad4a2d209496 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 14:47:43 +0530
Subject: [PATCH v5 6/8] pg_verifybackup: Delay default WAL directory
 preparation.

We are not sure whether to parse WAL from a directory or an archive
until the backup format is known. Therefore, we delay preparing the
default WAL directory until the point of parsing. This delay is
harmless, as the WAL directory is not used elsewhere.
---
 src/bin/pg_verifybackup/pg_verifybackup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 5e6c13bb921..31ebc1581fb 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -285,10 +285,6 @@ main(int argc, char **argv)
 		manifest_path = psprintf("%s/backup_manifest",
 								 context.backup_directory);
 
-	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
-
 	/*
 	 * Try to read the manifest. We treat any errors encountered while parsing
 	 * the manifest as fatal; there doesn't seem to be much point in trying to
@@ -368,6 +364,10 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
+	/* By default, look for the WAL in the backup directory, too. */
+	if (wal_directory == NULL)
+		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
-- 
2.47.1

From 33299daf17137bded756aedbe122232cc4ecc244 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 24 Jul 2025 16:37:43 +0530
Subject: [PATCH v5 7/8] pg_verifybackup: Rename the wal-directory switch to
 wal-path

With previous patches to pg_waldump can now decode WAL directly from
tar files.  This means you'll be able to specify a tar archive path
instead of a traditional WAL directory.

To keep things consistent and more versatile, we should also
generalize the input switch for pg_verifybackup. It should accept
either a directory or a tar file path that contains WALs. This change
will also aligning it with the existing manifest-path switch naming.
---
 doc/src/sgml/ref/pg_verifybackup.sgml     |  2 +-
 src/bin/pg_verifybackup/pg_verifybackup.c | 22 +++++++++++-----------
 src/bin/pg_verifybackup/po/de.po          |  4 ++--
 src/bin/pg_verifybackup/po/el.po          |  4 ++--
 src/bin/pg_verifybackup/po/es.po          |  4 ++--
 src/bin/pg_verifybackup/po/fr.po          |  4 ++--
 src/bin/pg_verifybackup/po/it.po          |  4 ++--
 src/bin/pg_verifybackup/po/ja.po          |  4 ++--
 src/bin/pg_verifybackup/po/ka.po          |  4 ++--
 src/bin/pg_verifybackup/po/ko.po          |  4 ++--
 src/bin/pg_verifybackup/po/ru.po          |  4 ++--
 src/bin/pg_verifybackup/po/sv.po          |  4 ++--
 src/bin/pg_verifybackup/po/uk.po          |  4 ++--
 src/bin/pg_verifybackup/po/zh_CN.po       |  4 ++--
 src/bin/pg_verifybackup/po/zh_TW.po       |  4 ++--
 src/bin/pg_verifybackup/t/007_wal.pl      |  4 ++--
 16 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index 61c12975e4a..e9b8bfd51b1 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -261,7 +261,7 @@ PostgreSQL documentation
 
      <varlistentry>
       <term><option>-w <replaceable class="parameter">path</replaceable></option></term>
-      <term><option>--wal-directory=<replaceable class="parameter">path</replaceable></option></term>
+      <term><option>--wal-path=<replaceable class="parameter">path</replaceable></option></term>
       <listitem>
        <para>
         Try to parse WAL files stored in the specified directory, rather than
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 31ebc1581fb..1ee400199da 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -93,7 +93,7 @@ static void verify_file_checksum(verifier_context *context,
 								 uint8 *buffer);
 static void parse_required_wal(verifier_context *context,
 							   char *pg_waldump_path,
-							   char *wal_directory);
+							   char *wal_path);
 static astreamer *create_archive_verifier(verifier_context *context,
 										  char *archive_name,
 										  Oid tblspc_oid,
@@ -126,7 +126,7 @@ main(int argc, char **argv)
 		{"progress", no_argument, NULL, 'P'},
 		{"quiet", no_argument, NULL, 'q'},
 		{"skip-checksums", no_argument, NULL, 's'},
-		{"wal-directory", required_argument, NULL, 'w'},
+		{"wal-path", required_argument, NULL, 'w'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -135,7 +135,7 @@ main(int argc, char **argv)
 	char	   *manifest_path = NULL;
 	bool		no_parse_wal = false;
 	bool		quiet = false;
-	char	   *wal_directory = NULL;
+	char	   *wal_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -221,8 +221,8 @@ main(int argc, char **argv)
 				context.skip_checksums = true;
 				break;
 			case 'w':
-				wal_directory = pstrdup(optarg);
-				canonicalize_path(wal_directory);
+				wal_path = pstrdup(optarg);
+				canonicalize_path(wal_path);
 				break;
 			default:
 				/* getopt_long already emitted a complaint */
@@ -365,15 +365,15 @@ main(int argc, char **argv)
 		verify_backup_checksums(&context);
 
 	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+	if (wal_path == NULL)
+		wal_path = psprintf("%s/pg_wal", context.backup_directory);
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
 	 */
 	if (!no_parse_wal)
-		parse_required_wal(&context, pg_waldump_path, wal_directory);
+		parse_required_wal(&context, pg_waldump_path, wal_path);
 
 	/*
 	 * If everything looks OK, tell the user this, unless we were asked to
@@ -1198,7 +1198,7 @@ verify_file_checksum(verifier_context *context, manifest_file *m,
  */
 static void
 parse_required_wal(verifier_context *context, char *pg_waldump_path,
-				   char *wal_directory)
+				   char *wal_path)
 {
 	manifest_data *manifest = context->manifest;
 	manifest_wal_range *this_wal_range = manifest->first_wal_range;
@@ -1208,7 +1208,7 @@ parse_required_wal(verifier_context *context, char *pg_waldump_path,
 		char	   *pg_waldump_cmd;
 
 		pg_waldump_cmd = psprintf("\"%s\" --quiet --path=\"%s\" --timeline=%u --start=%X/%08X --end=%X/%08X\n",
-								  pg_waldump_path, wal_directory, this_wal_range->tli,
+								  pg_waldump_path, wal_path, this_wal_range->tli,
 								  LSN_FORMAT_ARGS(this_wal_range->start_lsn),
 								  LSN_FORMAT_ARGS(this_wal_range->end_lsn));
 		fflush(NULL);
@@ -1376,7 +1376,7 @@ usage(void)
 	printf(_("  -P, --progress              show progress information\n"));
 	printf(_("  -q, --quiet                 do not print any output, except for errors\n"));
 	printf(_("  -s, --skip-checksums        skip checksum verification\n"));
-	printf(_("  -w, --wal-directory=PATH    use specified path for WAL files\n"));
+	printf(_("  -w, --wal-path=PATH         use specified path for WAL files\n"));
 	printf(_("  -V, --version               output version information, then exit\n"));
 	printf(_("  -?, --help                  show this help, then exit\n"));
 	printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
diff --git a/src/bin/pg_verifybackup/po/de.po b/src/bin/pg_verifybackup/po/de.po
index a9e24931100..9b5cd5898cf 100644
--- a/src/bin/pg_verifybackup/po/de.po
+++ b/src/bin/pg_verifybackup/po/de.po
@@ -785,8 +785,8 @@ msgstr "  -s, --skip-checksums        Überprüfung der Prüfsummen überspringe
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/el.po b/src/bin/pg_verifybackup/po/el.po
index 3e3f20c67c5..81442f51c17 100644
--- a/src/bin/pg_verifybackup/po/el.po
+++ b/src/bin/pg_verifybackup/po/el.po
@@ -494,8 +494,8 @@ msgstr "  -s, --skip-checksums        παράκαμψε την επαλήθευ
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/es.po b/src/bin/pg_verifybackup/po/es.po
index 0cb958f3448..7f729fa35ba 100644
--- a/src/bin/pg_verifybackup/po/es.po
+++ b/src/bin/pg_verifybackup/po/es.po
@@ -495,8 +495,8 @@ msgstr "  -s, --skip-checksums        omitir la verificación de la suma de comp
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    utilizar la ruta especificada para los archivos WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    utilizar la ruta especificada para los archivos WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/fr.po b/src/bin/pg_verifybackup/po/fr.po
index da8c72f6427..09937966fa7 100644
--- a/src/bin/pg_verifybackup/po/fr.po
+++ b/src/bin/pg_verifybackup/po/fr.po
@@ -498,8 +498,8 @@ msgstr "  -s, --skip-checksums        ignore la vérification des sommes de cont
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/it.po b/src/bin/pg_verifybackup/po/it.po
index 317b0b71e7f..4da68d0074e 100644
--- a/src/bin/pg_verifybackup/po/it.po
+++ b/src/bin/pg_verifybackup/po/it.po
@@ -472,8 +472,8 @@ msgstr "  -s, --skip-checksums         salta la verifica del checksum\n"
 
 #: pg_verifybackup.c:911
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH     usa il percorso specificato per i file WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH     usa il percorso specificato per i file WAL\n"
 
 #: pg_verifybackup.c:912
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ja.po b/src/bin/pg_verifybackup/po/ja.po
index c910fb236cc..a948959b54f 100644
--- a/src/bin/pg_verifybackup/po/ja.po
+++ b/src/bin/pg_verifybackup/po/ja.po
@@ -672,8 +672,8 @@ msgstr "  -s, --skip-checksums        チェックサム検証をスキップ\n"
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    WALファイルに指定したパスを使用する\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    WALファイルに指定したパスを使用する\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ka.po b/src/bin/pg_verifybackup/po/ka.po
index 982751984c7..ef2799316a8 100644
--- a/src/bin/pg_verifybackup/po/ka.po
+++ b/src/bin/pg_verifybackup/po/ka.po
@@ -784,8 +784,8 @@ msgstr "  -s, --skip-checksums        საკონტროლო ჯამ
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ko.po b/src/bin/pg_verifybackup/po/ko.po
index acdc3da5e02..eaf91ef1e98 100644
--- a/src/bin/pg_verifybackup/po/ko.po
+++ b/src/bin/pg_verifybackup/po/ko.po
@@ -501,8 +501,8 @@ msgstr "  -s, --skip-checksums        체크섬 검사 건너뜀\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=경로    WAL 파일이 있는 경로 지정\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=경로    WAL 파일이 있는 경로 지정\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ru.po b/src/bin/pg_verifybackup/po/ru.po
index 64005feedfd..7fb0e5ab1f6 100644
--- a/src/bin/pg_verifybackup/po/ru.po
+++ b/src/bin/pg_verifybackup/po/ru.po
@@ -507,9 +507,9 @@ msgstr "  -s, --skip-checksums        пропустить проверку ко
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
 msgstr ""
-"  -w, --wal-directory=ПУТЬ    использовать заданный путь к файлам WAL\n"
+"  -w, --wal-path=ПУТЬ    использовать заданный путь к файлам WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/sv.po b/src/bin/pg_verifybackup/po/sv.po
index 17240feeb5c..97125838e8c 100644
--- a/src/bin/pg_verifybackup/po/sv.po
+++ b/src/bin/pg_verifybackup/po/sv.po
@@ -492,8 +492,8 @@ msgstr "  -s, --skip-checksums        hoppa över verifiering av kontrollsummor\
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=SÖKVÄG  använd denna sökväg till WAL-filer\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=SÖKVÄG  använd denna sökväg till WAL-filer\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/uk.po b/src/bin/pg_verifybackup/po/uk.po
index 034b9764232..63f8041ab38 100644
--- a/src/bin/pg_verifybackup/po/uk.po
+++ b/src/bin/pg_verifybackup/po/uk.po
@@ -484,8 +484,8 @@ msgstr "  -s, --skip-checksums не перевіряти контрольні с
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH використовувати вказаний шлях для файлів WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH використовувати вказаний шлях для файлів WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_CN.po b/src/bin/pg_verifybackup/po/zh_CN.po
index b7d97c8976d..fb6fcae8b82 100644
--- a/src/bin/pg_verifybackup/po/zh_CN.po
+++ b/src/bin/pg_verifybackup/po/zh_CN.po
@@ -465,8 +465,8 @@ msgstr "  -s, --skip-checksums        跳过校验和验证\n"
 
 #: pg_verifybackup.c:919
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    对WAL文件使用指定路径\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    对WAL文件使用指定路径\n"
 
 #: pg_verifybackup.c:920
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_TW.po b/src/bin/pg_verifybackup/po/zh_TW.po
index c1b710b0a36..568f972b0bb 100644
--- a/src/bin/pg_verifybackup/po/zh_TW.po
+++ b/src/bin/pg_verifybackup/po/zh_TW.po
@@ -555,8 +555,8 @@ msgstr "  -s, --skip-checksums        跳過檢查碼驗證\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    用指定的路徑存放 WAL 檔\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    用指定的路徑存放 WAL 檔\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/t/007_wal.pl b/src/bin/pg_verifybackup/t/007_wal.pl
index babc4f0a86b..b07f80719b0 100644
--- a/src/bin/pg_verifybackup/t/007_wal.pl
+++ b/src/bin/pg_verifybackup/t/007_wal.pl
@@ -42,10 +42,10 @@ command_ok([ 'pg_verifybackup', '--no-parse-wal', $backup_path ],
 command_ok(
 	[
 		'pg_verifybackup',
-		'--wal-directory' => $relocated_pg_wal,
+		'--wal-path' => $relocated_pg_wal,
 		$backup_path
 	],
-	'--wal-directory can be used to specify WAL directory');
+	'--wal-path can be used to specify WAL directory');
 
 # Move directory back to original location.
 rename($relocated_pg_wal, $original_pg_wal) || die "rename pg_wal back: $!";
-- 
2.47.1

From 2498f315388fc8a1a840a2b883bca107b0113c0e Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 17 Jul 2025 16:39:36 +0530
Subject: [PATCH v5 8/8] pg_verifybackup: enabled WAL parsing for tar-format
 backup

Now that pg_waldump supports decoding from tar archives, we should
leverage this functionality to remove the previous restriction on WAL
parsing for tar-backed formats.
---
 doc/src/sgml/ref/pg_verifybackup.sgml         |  5 +-
 src/bin/pg_verifybackup/pg_verifybackup.c     | 66 +++++++++++++------
 src/bin/pg_verifybackup/t/002_algorithm.pl    |  4 --
 src/bin/pg_verifybackup/t/003_corruption.pl   |  4 +-
 src/bin/pg_verifybackup/t/008_untar.pl        |  5 +-
 src/bin/pg_verifybackup/t/010_client_untar.pl |  5 +-
 6 files changed, 50 insertions(+), 39 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index e9b8bfd51b1..16b50b5a4df 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -36,10 +36,7 @@ PostgreSQL documentation
    <literal>backup_manifest</literal> generated by the server at the time
    of the backup. The backup may be stored either in the "plain" or the "tar"
    format; this includes tar-format backups compressed with any algorithm
-   supported by <application>pg_basebackup</application>. However, at present,
-   <literal>WAL</literal> verification is supported only for plain-format
-   backups. Therefore, if the backup is stored in tar-format, the
-   <literal>-n, --no-parse-wal</literal> option should be used.
+   supported by <application>pg_basebackup</application>.
   </para>
 
   <para>
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 1ee400199da..4bfe6fdff16 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -74,7 +74,9 @@ pg_noreturn static void report_manifest_error(JsonManifestParseContext *context,
 											  const char *fmt,...)
 			pg_attribute_printf(2, 3);
 
-static void verify_tar_backup(verifier_context *context, DIR *dir);
+static void verify_tar_backup(verifier_context *context, DIR *dir,
+							  char **base_archive_path,
+							  char **wal_archive_path);
 static void verify_plain_backup_directory(verifier_context *context,
 										  char *relpath, char *fullpath,
 										  DIR *dir);
@@ -83,7 +85,9 @@ static void verify_plain_backup_file(verifier_context *context, char *relpath,
 static void verify_control_file(const char *controlpath,
 								uint64 manifest_system_identifier);
 static void precheck_tar_backup_file(verifier_context *context, char *relpath,
-									 char *fullpath, SimplePtrList *tarfiles);
+									 char *fullpath, SimplePtrList *tarfiles,
+									 char **base_archive_path,
+									 char **wal_archive_path);
 static void verify_tar_file(verifier_context *context, char *relpath,
 							char *fullpath, astreamer *streamer);
 static void report_extra_backup_files(verifier_context *context);
@@ -136,6 +140,8 @@ main(int argc, char **argv)
 	bool		no_parse_wal = false;
 	bool		quiet = false;
 	char	   *wal_path = NULL;
+	char	   *base_archive_path = NULL;
+	char	   *wal_archive_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -327,17 +333,6 @@ main(int argc, char **argv)
 		pfree(path);
 	}
 
-	/*
-	 * XXX: In the future, we should consider enhancing pg_waldump to read WAL
-	 * files from an archive.
-	 */
-	if (!no_parse_wal && context.format == 't')
-	{
-		pg_log_error("pg_waldump cannot read tar files");
-		pg_log_error_hint("You must use -n/--no-parse-wal when verifying a tar-format backup.");
-		exit(1);
-	}
-
 	/*
 	 * Perform the appropriate type of verification appropriate based on the
 	 * backup format. This will close 'dir'.
@@ -346,7 +341,7 @@ main(int argc, char **argv)
 		verify_plain_backup_directory(&context, NULL, context.backup_directory,
 									  dir);
 	else
-		verify_tar_backup(&context, dir);
+		verify_tar_backup(&context, dir, &base_archive_path, &wal_archive_path);
 
 	/*
 	 * The "matched" flag should now be set on every entry in the hash table.
@@ -364,9 +359,28 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
-	/* By default, look for the WAL in the backup directory, too. */
+	/*
+	 * By default, WAL files are expected to be found in the backup directory
+	 * for plain-format backups. In the case of tar-format backups, if a
+	 * separate WAL archive is not found, the WAL files are most likely
+	 * included within the main data directory archive.
+	 */
 	if (wal_path == NULL)
-		wal_path = psprintf("%s/pg_wal", context.backup_directory);
+	{
+		if (context.format == 'p')
+			wal_path = psprintf("%s/pg_wal", context.backup_directory);
+		else if (wal_archive_path)
+			wal_path = wal_archive_path;
+		else if (base_archive_path)
+			wal_path = base_archive_path;
+		else
+		{
+			pg_log_error("wal archive not found");
+			pg_log_error_hint("Specify the correct path using the option -w/--wal-path."
+							  "Or you must use -n/--no-parse-wal when verifying a tar-format backup.");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
@@ -787,7 +801,8 @@ verify_control_file(const char *controlpath, uint64 manifest_system_identifier)
  * close when we're done with it.
  */
 static void
-verify_tar_backup(verifier_context *context, DIR *dir)
+verify_tar_backup(verifier_context *context, DIR *dir, char **base_archive_path,
+				  char **wal_archive_path)
 {
 	struct dirent *dirent;
 	SimplePtrList tarfiles = {NULL, NULL};
@@ -816,7 +831,8 @@ verify_tar_backup(verifier_context *context, DIR *dir)
 			char	   *fullpath;
 
 			fullpath = psprintf("%s/%s", context->backup_directory, filename);
-			precheck_tar_backup_file(context, filename, fullpath, &tarfiles);
+			precheck_tar_backup_file(context, filename, fullpath, &tarfiles,
+									 base_archive_path, wal_archive_path);
 			pfree(fullpath);
 		}
 	}
@@ -875,11 +891,13 @@ verify_tar_backup(verifier_context *context, DIR *dir)
  *
  * The arguments to this function are mostly the same as the
  * verify_plain_backup_file. The additional argument outputs a list of valid
- * tar files.
+ * tar files, along with the full paths to the main archive and the WAL
+ * directory archive.
  */
 static void
 precheck_tar_backup_file(verifier_context *context, char *relpath,
-						 char *fullpath, SimplePtrList *tarfiles)
+						 char *fullpath, SimplePtrList *tarfiles,
+						 char **base_archive_path, char **wal_archive_path)
 {
 	struct stat sb;
 	Oid			tblspc_oid = InvalidOid;
@@ -918,9 +936,17 @@ precheck_tar_backup_file(verifier_context *context, char *relpath,
 	 * extension such as .gz, .lz4, or .zst.
 	 */
 	if (strncmp("base", relpath, 4) == 0)
+	{
 		suffix = relpath + 4;
+
+		*base_archive_path = pstrdup(fullpath);
+	}
 	else if (strncmp("pg_wal", relpath, 6) == 0)
+	{
 		suffix = relpath + 6;
+
+		*wal_archive_path = pstrdup(fullpath);
+	}
 	else
 	{
 		/* Expected a <tablespaceoid>.tar file here. */
diff --git a/src/bin/pg_verifybackup/t/002_algorithm.pl b/src/bin/pg_verifybackup/t/002_algorithm.pl
index ae16c11bc4d..4f284a9e828 100644
--- a/src/bin/pg_verifybackup/t/002_algorithm.pl
+++ b/src/bin/pg_verifybackup/t/002_algorithm.pl
@@ -30,10 +30,6 @@ sub test_checksums
 	{
 		# Add switch to get a tar-format backup
 		push @backup, ('--format' => 'tar');
-
-		# Add switch to skip WAL verification, which is not yet supported for
-		# tar-format backups
-		push @verify, ('--no-parse-wal');
 	}
 
 	# A backup with a bogus algorithm should fail.
diff --git a/src/bin/pg_verifybackup/t/003_corruption.pl b/src/bin/pg_verifybackup/t/003_corruption.pl
index 1dd60f709cf..f1ebdbb46b4 100644
--- a/src/bin/pg_verifybackup/t/003_corruption.pl
+++ b/src/bin/pg_verifybackup/t/003_corruption.pl
@@ -193,10 +193,8 @@ for my $scenario (@scenario)
 			command_ok([ $tar, '-cf' => "$tar_backup_path/base.tar", '.' ]);
 			chdir($cwd) || die "chdir: $!";
 
-			# Now check that the backup no longer verifies. We must use -n
-			# here, because pg_waldump can't yet read WAL from a tarfile.
 			command_fails_like(
-				[ 'pg_verifybackup', '--no-parse-wal', $tar_backup_path ],
+				[ 'pg_verifybackup', $tar_backup_path ],
 				$scenario->{'fails_like'},
 				"corrupt backup fails verification: $name");
 
diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index bc3d6b352ad..09079a94fee 100644
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -47,7 +47,6 @@ my $tsoid = $primary->safe_psql(
 		SELECT oid FROM pg_tablespace WHERE spcname = 'regress_ts1'));
 
 my $backup_path = $primary->backup_dir . '/server-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -123,14 +122,12 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
 		rmtree($backup_path);
-		rmtree($extract_path);
 	}
 }
 
diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index b62faeb5acf..5b0e76ee69d 100644
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -32,7 +32,6 @@ print $jf $junk_data;
 close $jf;
 
 my $backup_path = $primary->backup_dir . '/client-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -137,13 +136,11 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
-		rmtree($extract_path);
 		rmtree($backup_path);
 	}
 }
-- 
2.47.1

From f56a3ce0343d9f539f638b88445aefb256afbfb5 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 24 Jun 2025 11:33:20 +0530
Subject: [PATCH v6 1/8] Refactor: pg_waldump: Move some declarations to new
 pg_waldump.h

This change prepares for a second source file in this directory to
support reading WAL from tar files. Common structures, declarations,
and functions are being exported through this include file so
they can be used in both files.
---
 src/bin/pg_waldump/pg_waldump.c | 11 ++---------
 src/bin/pg_waldump/pg_waldump.h | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 9 deletions(-)
 create mode 100644 src/bin/pg_waldump/pg_waldump.h

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index c6d6ba79e44..5846ee24f46 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -29,6 +29,7 @@
 #include "common/logging.h"
 #include "common/relpath.h"
 #include "getopt_long.h"
+#include "pg_waldump.h"
 #include "rmgrdesc.h"
 #include "storage/bufpage.h"
 
@@ -39,19 +40,11 @@
 
 static const char *progname;
 
-static int	WalSegSz;
+int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 static volatile sig_atomic_t time_to_stop = false;
 
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
-typedef struct XLogDumpPrivate
-{
-	TimeLineID	timeline;
-	XLogRecPtr	startptr;
-	XLogRecPtr	endptr;
-	bool		endptr_reached;
-} XLogDumpPrivate;
-
 typedef struct XLogDumpConfig
 {
 	/* display options */
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
new file mode 100644
index 00000000000..9e62b64ead5
--- /dev/null
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -0,0 +1,27 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_waldump.h - decode and display WAL
+ *
+ * Copyright (c) 2013-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  src/bin/pg_waldump/pg_waldump.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_WALDUMP_H
+#define PG_WALDUMP_H
+
+#include "access/xlogdefs.h"
+
+extern int	WalSegSz;
+
+/* Contains the necessary information to drive WAL decoding */
+typedef struct XLogDumpPrivate
+{
+	TimeLineID	timeline;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
+	bool		endptr_reached;
+} XLogDumpPrivate;
+
+#endif		/* end of PG_WALDUMP_H */
-- 
2.47.1

From 835cce8a5ed331215cf6c77075ed0ddea06ee859 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 26 Jun 2025 11:42:53 +0530
Subject: [PATCH v6 2/8] Refactor: pg_waldump: Separate logic used to calculate
 the required read size.

This refactoring prepares the codebase for an upcoming patch that will
support reading WAL from tar files. The logic for calculating the
required read size has been updated to handle both normal WAL files
and WAL files located inside a tar archive.
---
 src/bin/pg_waldump/pg_waldump.c | 39 ++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 5846ee24f46..0dc28ea360c 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -326,6 +326,29 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/* Returns the size in bytes of the data to be read. */
+static inline int
+required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
+				  int reqLen)
+{
+	int			count = XLOG_BLCKSZ;
+
+	if (XLogRecPtrIsValid(private->endptr))
+	{
+		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
+			count = XLOG_BLCKSZ;
+		else if (targetPagePtr + reqLen <= private->endptr)
+			count = private->endptr - targetPagePtr;
+		else
+		{
+			private->endptr_reached = true;
+			return -1;
+		}
+	}
+
+	return count;
+}
+
 /* pg_waldump's XLogReaderRoutine->segment_open callback */
 static void
 WALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
@@ -383,21 +406,11 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = XLOG_BLCKSZ;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
-	if (XLogRecPtrIsValid(private->endptr))
-	{
-		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
-			count = XLOG_BLCKSZ;
-		else if (targetPagePtr + reqLen <= private->endptr)
-			count = private->endptr - targetPagePtr;
-		else
-		{
-			private->endptr_reached = true;
-			return -1;
-		}
-	}
+	if (private->endptr_reached)
+		return -1;
 
 	if (!WALRead(state, readBuff, targetPagePtr, count, private->timeline,
 				 &errinfo))
-- 
2.47.1

From b4d347153a0b1eed353a0549331a52c232aa04ac Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 30 Jul 2025 12:43:30 +0530
Subject: [PATCH v6 3/8] Refactor: pg_waldump: Restructure TAP tests.

Restructured some tests to run inside a loop, facilitating their
re-execution for decoding WAL from tar archives.
---
 src/bin/pg_waldump/t/001_basic.pl | 123 ++++++++++++++++--------------
 1 file changed, 67 insertions(+), 56 deletions(-)

diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index f26d75e01cf..1b712e8d74d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -198,28 +198,6 @@ command_like(
 	],
 	qr/./,
 	'runs with start and end segment specified');
-command_fails_like(
-	[ 'pg_waldump', '--path' => $node->data_dir ],
-	qr/error: no start WAL location given/,
-	'path option requires start location');
-command_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-		'--end' => $end_lsn,
-	],
-	qr/./,
-	'runs with path option and start and end locations');
-command_fails_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-	],
-	qr/error: error in WAL record at/,
-	'falling off the end of the WAL results in an error');
-
 command_like(
 	[
 		'pg_waldump', '--quiet',
@@ -227,15 +205,6 @@ command_like(
 	],
 	qr/^$/,
 	'no output with --quiet option');
-command_fails_like(
-	[
-		'pg_waldump', '--quiet',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn
-	],
-	qr/error: error in WAL record at/,
-	'errors are shown with --quiet');
-
 
 # Test for: Display a message that we're skipping data if `from`
 # wasn't a pointer to the start of a record.
@@ -272,7 +241,6 @@ sub test_pg_waldump
 
 	my $result = IPC::Run::run [
 		'pg_waldump',
-		'--path' => $node->data_dir,
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
 		@opts
@@ -288,38 +256,81 @@ sub test_pg_waldump
 
 my @lines;
 
-@lines = test_pg_waldump;
-is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
+my @scenario = (
+	{
+		'path' => $node->data_dir
+	});
 
-@lines = test_pg_waldump('--limit' => 6);
-is(@lines, 6, 'limit option observed');
+for my $scenario (@scenario)
+{
+	my $path = $scenario->{'path'};
 
-@lines = test_pg_waldump('--fullpage');
-is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
+	SKIP:
+	{
+		command_fails_like(
+			[ 'pg_waldump', '--path' => $path ],
+			qr/error: no start WAL location given/,
+			'path option requires start location');
+		command_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+				'--end' => $end_lsn,
+			],
+			qr/./,
+			'runs with path option and start and end locations');
+		command_fails_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+			],
+			qr/error: error in WAL record at/,
+			'falling off the end of the WAL results in an error');
 
-@lines = test_pg_waldump('--stats');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		command_fails_like(
+			[
+				'pg_waldump', '--quiet',
+				'--path' => $path,
+				'--start' => $start_lsn
+			],
+			qr/error: error in WAL record at/,
+			'errors are shown with --quiet');
 
-@lines = test_pg_waldump('--stats=record');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		@lines = test_pg_waldump('--path' => $path);
+		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-@lines = test_pg_waldump('--rmgr' => 'Btree');
-is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		is(@lines, 6, 'limit option observed');
 
-@lines = test_pg_waldump('--fork' => 'init');
-is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
-is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
-	0, 'only lines for selected relation');
+		@lines = test_pg_waldump('--path' => $path, '--stats');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
-	'--block' => 1);
-is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
+		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+
+		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
+		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
+			0, 'only lines for selected relation');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
+			'--block' => 1);
+		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+	}
+}
 
 done_testing();
-- 
2.47.1

From 187e47acc12b4983a13c9c4aad7fbc66f92db0f6 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 5 Nov 2025 15:40:36 +0530
Subject: [PATCH v6 4/8] pg_waldump: Add support for archived WAL decoding.

pg_waldump can now accept the path to a tar archive containing WAL
files and decode them. This feature was added primarily for
pg_verifybackup, which previously disabled WAL parsing for
tar-formatted backups.

Note that this patch requires that the WAL files within the archive be
in sequential order; an error will be reported otherwise. The next
patch is planned to remove this restriction.
---
 doc/src/sgml/ref/pg_waldump.sgml     |   8 +-
 src/bin/pg_waldump/Makefile          |   7 +-
 src/bin/pg_waldump/archive_waldump.c | 577 +++++++++++++++++++++++++++
 src/bin/pg_waldump/meson.build       |   4 +-
 src/bin/pg_waldump/pg_waldump.c      | 217 +++++++---
 src/bin/pg_waldump/pg_waldump.h      |  36 +-
 src/bin/pg_waldump/t/001_basic.pl    |  84 +++-
 src/tools/pgindent/typedefs.list     |   3 +
 8 files changed, 860 insertions(+), 76 deletions(-)
 create mode 100644 src/bin/pg_waldump/archive_waldump.c

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index ce23add5577..d004bb0f67e 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -141,13 +141,17 @@ PostgreSQL documentation
       <term><option>--path=<replaceable>path</replaceable></option></term>
       <listitem>
        <para>
-        Specifies a directory to search for WAL segment files or a
-        directory with a <literal>pg_wal</literal> subdirectory that
+        Specifies a tar archive or a directory to search for WAL segment files
+        or a directory with a <literal>pg_wal</literal> subdirectory that
         contains such files.  The default is to search in the current
         directory, the <literal>pg_wal</literal> subdirectory of the
         current directory, and the <literal>pg_wal</literal> subdirectory
         of <envar>PGDATA</envar>.
        </para>
+       <para>
+        If a tar archive is provided, its WAL segment files must be in
+        sequential order; otherwise, an error will be reported.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index 4c1ee649501..05ac5763a57 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -3,6 +3,9 @@
 PGFILEDESC = "pg_waldump - decode and display WAL"
 PGAPPICON=win32
 
+# make these available to TAP test scripts
+export TAR
+
 subdir = src/bin/pg_waldump
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
@@ -12,11 +15,13 @@ OBJS = \
 	$(WIN32RES) \
 	compat.o \
 	pg_waldump.o \
+	archive_waldump.o \
 	rmgrdesc.o \
 	xlogreader.o \
 	xlogstats.o
 
-override CPPFLAGS := -DFRONTEND $(CPPFLAGS)
+override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
new file mode 100644
index 00000000000..2830c89a7be
--- /dev/null
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -0,0 +1,577 @@
+/*-------------------------------------------------------------------------
+ *
+ * archive_waldump.c
+ *		A generic facility for reading WAL data from tar archives via archive
+ *		streamer.
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/bin/pg_waldump/archive_waldump.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <unistd.h>
+
+#include "access/xlog_internal.h"
+#include "common/hashfn.h"
+#include "common/logging.h"
+#include "fe_utils/simple_list.h"
+#include "pg_waldump.h"
+
+/*
+ * How many bytes should we try to read from a file at once?
+ */
+#define READ_CHUNK_SIZE				(128 * 1024)
+
+/* Structure for storing the WAL segment data from the archive */
+typedef struct ArchivedWALEntry
+{
+	uint32		status;			/* hash status */
+	XLogSegNo	segno;			/* hash key: WAL segment number */
+	TimeLineID	timeline;		/* timeline of this wal file */
+
+	StringInfoData buf;
+	bool		tmpseg_exists;	/* spill file exists? */
+
+	int			total_read;		/* total read of this WAL segment, including
+								 * buffered and temporarily written data */
+} ArchivedWALEntry;
+
+#define SH_PREFIX				ArchivedWAL
+#define SH_ELEMENT_TYPE			ArchivedWALEntry
+#define SH_KEY_TYPE				XLogSegNo
+#define SH_KEY					segno
+#define SH_HASH_KEY(tb, key)	murmurhash64((uint64) key)
+#define SH_EQUAL(tb, a, b)		(a == b)
+#define SH_GET_HASH(tb, a)		a->hash
+#define SH_SCOPE				static inline
+#define SH_RAW_ALLOCATOR		pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static ArchivedWAL_hash *ArchivedWAL_HTAB = NULL;
+
+typedef struct astreamer_waldump
+{
+	astreamer	base;
+	XLogDumpPrivate *privateInfo;
+} astreamer_waldump;
+
+static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
+static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
+											   XLogDumpPrivate *privateInfo);
+
+static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
+static void astreamer_waldump_content(astreamer *streamer,
+									  astreamer_member *member,
+									  const char *data, int len,
+									  astreamer_archive_context context);
+static void astreamer_waldump_finalize(astreamer *streamer);
+static void astreamer_waldump_free(astreamer *streamer);
+
+static bool member_is_wal_file(astreamer_waldump *mystreamer,
+							   astreamer_member *member,
+							   XLogSegNo *curSegNo,
+							   TimeLineID *curTimeline);
+
+static const astreamer_ops astreamer_waldump_ops = {
+	.content = astreamer_waldump_content,
+	.finalize = astreamer_waldump_finalize,
+	.free = astreamer_waldump_free
+};
+
+/*
+ * Returns true if the given file is a tar archive and outputs its compression
+ * algorithm.
+ */
+bool
+is_archive_file(const char *fname, pg_compress_algorithm *compression)
+{
+	int			fname_len = strlen(fname);
+	pg_compress_algorithm compress_algo;
+
+	/* Now, check the compression type of the tar */
+	if (fname_len > 4 &&
+		strcmp(fname + fname_len - 4, ".tar") == 0)
+		compress_algo = PG_COMPRESSION_NONE;
+	else if (fname_len > 4 &&
+			 strcmp(fname + fname_len - 4, ".tgz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 7 &&
+			 strcmp(fname + fname_len - 7, ".tar.gz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.lz4") == 0)
+		compress_algo = PG_COMPRESSION_LZ4;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.zst") == 0)
+		compress_algo = PG_COMPRESSION_ZSTD;
+	else
+		return false;
+
+	*compression = compress_algo;
+
+	return true;
+}
+
+/*
+ * Initializes the tar archive reader to read WAL files from the archive,
+ * creates a hash table to store them, performs quick existence checks for WAL
+ * entries in the archive and retrieves the WAL segment size, and sets up
+ * filtering criteria for relevant entries.
+ */
+void
+init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
+					pg_compress_algorithm compression)
+{
+	int			fd;
+	astreamer  *streamer;
+	ArchivedWALEntry *entry = NULL;
+	XLogLongPageHeader longhdr;
+
+	/* Open tar archive and store its file descriptor */
+	fd = open_file_in_directory(waldir, privateInfo->archive_name);
+
+	if (fd < 0)
+		pg_fatal("could not open file \"%s\"", privateInfo->archive_name);
+
+	privateInfo->archive_fd = fd;
+
+	streamer = astreamer_waldump_new(privateInfo);
+
+	/* Before that we must parse the tar archive. */
+	streamer = astreamer_tar_parser_new(streamer);
+
+	/* Before that we must decompress, if archive is compressed. */
+	if (compression == PG_COMPRESSION_GZIP)
+		streamer = astreamer_gzip_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_LZ4)
+		streamer = astreamer_lz4_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_ZSTD)
+		streamer = astreamer_zstd_decompressor_new(streamer);
+
+	privateInfo->archive_streamer = streamer;
+
+	/* Hash table storing WAL entries read from the archive */
+	ArchivedWAL_HTAB = ArchivedWAL_create(16, NULL);
+
+	/*
+	 * Verify that the archive contains valid WAL files and fetch WAL segment
+	 * size
+	 */
+	while (entry == NULL || entry->buf.len < XLOG_BLCKSZ)
+	{
+		if (read_archive_file(privateInfo, XLOG_BLCKSZ) == 0)
+			pg_fatal("could not find WAL in \"%s\" archive",
+					 privateInfo->archive_name);
+
+		entry = privateInfo->cur_wal;
+	}
+
+	/* Set WalSegSz if WAL data is successfully read */
+	longhdr = (XLogLongPageHeader) entry->buf.data;
+
+	WalSegSz = longhdr->xlp_seg_size;
+
+	if (!IsValidWalSegSize(WalSegSz))
+	{
+		pg_log_error(ngettext("invalid WAL segment size in WAL file from archive \"%s\" (%d byte)",
+							  "invalid WAL segment size in WAL file from archive \"%s\" (%d bytes)",
+							  WalSegSz),
+					 privateInfo->archive_name, WalSegSz);
+		pg_log_error_detail("The WAL segment size must be a power of two between 1 MB and 1 GB.");
+		exit(1);
+	}
+
+	/*
+	 * With the WAL segment size available, we can now initialize the
+	 * dependent start and end segment numbers.
+	 */
+	XLByteToSeg(privateInfo->startptr, privateInfo->startSegNo, WalSegSz);
+	XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+}
+
+/*
+ * Release the archive streamer chain and close the archive file.
+ */
+void
+free_archive_reader(XLogDumpPrivate *privateInfo)
+{
+	/*
+	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
+	 * flush any remaining buffered data or to ensure the end of the tar
+	 * archive is reached. However, when decoding a WAL file, once we hit the
+	 * end LSN, any remaining WAL data in the buffer or the tar archive's
+	 * unreached end can be safely ignored.
+	 */
+	astreamer_free(privateInfo->archive_streamer);
+
+	/* Close the file. */
+	if (close(privateInfo->archive_fd) != 0)
+		pg_log_error("could not close file \"%s\": %m",
+					 privateInfo->archive_name);
+}
+
+/*
+ * Copies WAL data from astreamer to readBuff; if unavailable, fetches more
+ * from the tar archive via astreamer.
+ */
+int
+read_archive_wal_page(XLogDumpPrivate *privateInfo, XLogRecPtr targetPagePtr,
+					  Size count, char *readBuff)
+{
+	char	   *p = readBuff;
+	Size		nbytes = count;
+	XLogRecPtr	recptr = targetPagePtr;
+	XLogSegNo	segno;
+	ArchivedWALEntry *entry;
+
+	XLByteToSeg(targetPagePtr, segno, WalSegSz);
+	entry = get_archive_wal_entry(segno, privateInfo);
+
+	while (nbytes > 0)
+	{
+		char	   *buf = entry->buf.data;
+		int			len = entry->buf.len;
+
+		/* WAL record range that the buffer contains */
+		XLogRecPtr	endPtr;
+		XLogRecPtr	startPtr;
+
+		XLogSegNoOffsetToRecPtr(entry->segno, entry->total_read,
+								WalSegSz, endPtr);
+		startPtr = endPtr - len;
+
+		Assert((endPtr - startPtr) == len);
+
+		/*
+		 * pg_waldump never ask the same WAL bytes more than once, so if we're
+		 * now being asked for data beyond the end of what we've already read,
+		 * that means none of the data we currently have in the buffer will
+		 * ever be consulted again. So, we can discard the existing buffer
+		 * contents and start over.
+		 */
+		if (recptr >= endPtr)
+		{
+			len = 0;
+
+			/* Discard the buffered data */
+			resetStringInfo(&entry->buf);
+		}
+
+		if (len > 0 && recptr > startPtr)
+		{
+			int			skipBytes = 0;
+
+			/*
+			 * The required offset is not at the start of the buffer, so skip
+			 * bytes until reaching the desired offset of the target page.
+			 */
+			skipBytes = recptr - startPtr;
+
+			buf += skipBytes;
+			len -= skipBytes;
+		}
+
+		if (len > 0)
+		{
+			int			readBytes = len >= nbytes ? nbytes : len;
+
+			/* Ensure reading correct WAL record */
+			Assert(recptr >= startPtr && recptr < endPtr);
+
+			memcpy(p, buf, readBytes);
+
+			/* Update state for read */
+			nbytes -= readBytes;
+			p += readBytes;
+			recptr += readBytes;
+		}
+		else
+		{
+			/*
+			 * Fetch more data; raise an error if it's not the current segment
+			 * being read by the archive streamer or if reading of the
+			 * archived file has finished.
+			 */
+			if (privateInfo->cur_wal != entry ||
+				read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+			{
+				char		fname[MAXFNAMELEN];
+
+				XLogFileName(fname, privateInfo->timeline, entry->segno,
+							 WalSegSz);
+				pg_fatal("could not read file \"%s\" from archive \"%s\": read %lld of %lld",
+						 fname, privateInfo->archive_name,
+						 (long long int) count - nbytes,
+						 (long long int) nbytes);
+			}
+		}
+	}
+
+	/*
+	 * Should have either have successfully read all the requested bytes or
+	 * reported a failure before this point.
+	 */
+	Assert(nbytes == 0);
+
+	/*
+	 * NB: We return the fixed value provided as input. Although we could
+	 * return a boolean since we either successfully read the WAL page or
+	 * raise an error, but the caller expects this value to be returned. The
+	 * routine that reads WAL pages from the physical WAL file follows the
+	 * same convention.
+	 */
+	return count;
+}
+
+/*
+ * Reads the archive file and passes it to the archive streamer for
+ * decompression.
+ */
+static int
+read_archive_file(XLogDumpPrivate *privateInfo, Size count)
+{
+	int			rc;
+	char	   *buffer;
+
+	buffer = pg_malloc(READ_CHUNK_SIZE * sizeof(uint8));
+
+	rc = read(privateInfo->archive_fd, buffer, count);
+	if (rc < 0)
+		pg_fatal("could not read file \"%s\": %m",
+				 privateInfo->archive_name);
+
+	/*
+	 * Decompress (if required), and then parse the previously read contents
+	 * of the tar file.
+	 */
+	if (rc > 0)
+		astreamer_content(privateInfo->archive_streamer, NULL,
+						  buffer, rc, ASTREAMER_UNKNOWN);
+	pg_free(buffer);
+
+	return rc;
+}
+
+/*
+ * Returns the archived WAL entry from the hash table if it exists. Otherwise,
+ * it invokes the routine to read the archived file and retrieve the entry if
+ * it is not already in hash table.
+ */
+static ArchivedWALEntry *
+get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
+{
+	ArchivedWALEntry *entry = NULL;
+	char		fname[MAXFNAMELEN];
+
+	/* Search hash table */
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry != NULL)
+		return entry;
+
+	/* Needed WAL yet to be decoded from archive, do the same */
+	while (1)
+	{
+		entry = privateInfo->cur_wal;
+
+		/* Fetch more data */
+		if (entry == NULL || entry->buf.len == 0)
+		{
+			if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+				break;			/* archive file ended */
+		}
+
+		/*
+		 * Either, here for the first time, or the archived streamer is
+		 * reading a non-WAL file or an irrelevant WAL file.
+		 */
+		if (entry == NULL)
+			continue;
+
+		/* Found the required entry */
+		if (entry->segno == segno)
+			return entry;
+
+		/*
+		 * Ignore if the timeline is different or the current segment is not
+		 * the desired one.
+		 */
+		if (privateInfo->timeline != entry->timeline ||
+			privateInfo->startSegNo > entry->segno ||
+			privateInfo->endSegNo < entry->segno)
+		{
+			privateInfo->cur_wal = NULL;
+			continue;
+		}
+
+		/* WAL segments must be archived in order */
+		pg_log_error("WAL files are not archived in sequential order");
+		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
+							segno, entry->segno);
+		exit(1);
+	}
+
+	/* Requested WAL segment not found */
+	XLogFileName(fname, privateInfo->timeline, segno, WalSegSz);
+	pg_fatal("could not find file \"%s\" in archive", fname);
+}
+
+/*
+ * Create an astreamer that can read WAL from tar file.
+ */
+static astreamer *
+astreamer_waldump_new(XLogDumpPrivate *privateInfo)
+{
+	astreamer_waldump *streamer;
+
+	streamer = palloc0(sizeof(astreamer_waldump));
+	*((const astreamer_ops **) &streamer->base.bbs_ops) =
+		&astreamer_waldump_ops;
+
+	streamer->privateInfo = privateInfo;
+
+	return &streamer->base;
+}
+
+/*
+ * Main entry point of the archive streamer for reading WAL data from a tar
+ * file. If a member is identified as a valid WAL file, a hash entry is created
+ * for it, and its contents are copied into that entry's buffer, making them
+ * accessible to the decoding routine.
+ */
+static void
+astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
+						  const char *data, int len,
+						  astreamer_archive_context context)
+{
+	astreamer_waldump *mystreamer = (astreamer_waldump *) streamer;
+	XLogDumpPrivate *privateInfo = mystreamer->privateInfo;
+
+	Assert(context != ASTREAMER_UNKNOWN);
+
+	switch (context)
+	{
+		case ASTREAMER_MEMBER_HEADER:
+			{
+				XLogSegNo	segno;
+				TimeLineID	timeline;
+				ArchivedWALEntry *entry;
+				bool		found;
+
+				pg_log_debug("reading \"%s\"", member->pathname);
+
+				if (!member_is_wal_file(mystreamer, member,
+										&segno, &timeline))
+					break;
+
+				entry = ArchivedWAL_insert(ArchivedWAL_HTAB, segno, &found);
+
+				/*
+				 * Shouldn't happen, but if it does, simply ignore the
+				 * duplicate WAL file.
+				 */
+				if (found)
+				{
+					pg_log_warning("ignoring duplicate WAL file found in archive: \"%s\"",
+								   member->pathname);
+					break;
+				}
+
+				initStringInfo(&entry->buf);
+				entry->timeline = timeline;
+				entry->total_read = 0;
+
+				privateInfo->cur_wal = entry;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_CONTENTS:
+			if (privateInfo->cur_wal)
+			{
+				appendBinaryStringInfo(&privateInfo->cur_wal->buf, data, len);
+				privateInfo->cur_wal->total_read += len;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_TRAILER:
+			privateInfo->cur_wal = NULL;
+			break;
+
+		case ASTREAMER_ARCHIVE_TRAILER:
+			break;
+
+		default:
+			/* Shouldn't happen. */
+			pg_fatal("unexpected state while parsing tar file");
+	}
+}
+
+/*
+ * End-of-stream processing for a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_finalize(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+}
+
+/*
+ * Free memory associated with a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_free(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+	pfree(streamer);
+}
+
+/*
+ * Returns true if the archive member name matches the WAL naming format. If
+ * successful, it also outputs the WAL segment number, and timeline.
+ */
+static bool
+member_is_wal_file(astreamer_waldump *mystreamer, astreamer_member *member,
+				   XLogSegNo *curSegNo, TimeLineID *curTimeline)
+{
+	int			pathlen;
+	XLogSegNo	segNo;
+	TimeLineID	timeline;
+	char	   *fname;
+
+	/* We are only interested in normal files. */
+	if (member->is_directory || member->is_link)
+		return false;
+
+	pathlen = strlen(member->pathname);
+	if (pathlen < XLOG_FNAME_LEN)
+		return false;
+
+	/* WAL file could be with full path */
+	fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+	if (!IsXLogFileName(fname))
+		return false;
+
+	/*
+	 * XXX: On some systems (e.g., OpenBSD), the tar utility includes
+	 * PaxHeaders when creating an archive. These are special entries that
+	 * store extended metadata for the file entry immediately following them,
+	 * and they share the exact same name as that file.
+	 */
+	if (strstr(member->pathname, "PaxHeaders."))
+		return false;
+
+	/* Parse position from file */
+	XLogFromFileName(fname, &timeline, &segNo, WalSegSz);
+
+	*curSegNo = segNo;
+	*curTimeline = timeline;
+
+	return true;
+}
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 937e0d68841..da00746587c 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -3,6 +3,7 @@
 pg_waldump_sources = files(
   'compat.c',
   'pg_waldump.c',
+  'archive_waldump.c',
   'rmgrdesc.c',
 )
 
@@ -18,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, lz4, zstd],
+  dependencies: [frontend_code, lz4, zstd, libpq],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
@@ -29,6 +30,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'TAR': tar.found() ? tar.full_path() : ''},
     'tests': [
       't/001_basic.pl',
       't/002_save_fullpage.pl',
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 0dc28ea360c..7425d386d0c 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -177,7 +177,7 @@ split_path(const char *path, char **dir, char **fname)
  *
  * return a read only fd
  */
-static int
+int
 open_file_in_directory(const char *directory, const char *fname)
 {
 	int			fd = -1;
@@ -436,6 +436,44 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 	return count;
 }
 
+/*
+ * pg_waldump's XLogReaderRoutine->segment_open callback to support dumping WAL
+ * files from tar archives.
+ */
+static void
+TarWALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
+					  TimeLineID *tli_p)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->segment_close callback.
+ */
+static void
+TarWALDumpCloseSegment(XLogReaderState *state)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->page_read callback to support dumping WAL
+ * files from tar archives.
+ */
+static int
+TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				   XLogRecPtr targetPtr, char *readBuff)
+{
+	XLogDumpPrivate *private = state->private_data;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
+
+	if (private->endptr_reached)
+		return -1;
+
+	/* Read the WAL page from the archive streamer */
+	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
+}
+
 /*
  * Boolean to return whether the given WAL record matches a specific relation
  * and optionally block.
@@ -773,8 +811,8 @@ usage(void)
 	printf(_("  -F, --fork=FORK        only show records that modify blocks in fork FORK;\n"
 			 "                         valid names are main, fsm, vm, init\n"));
 	printf(_("  -n, --limit=N          number of records to display\n"));
-	printf(_("  -p, --path=PATH        directory in which to find WAL segment files or a\n"
-			 "                         directory with a ./pg_wal that contains such files\n"
+	printf(_("  -p, --path=PATH        tar archive or a directory in which to find WAL segment files or\n"
+			 "                         a directory with a ./pg_wal that contains such files\n"
 			 "                         (default: current directory, ./pg_wal, $PGDATA/pg_wal)\n"));
 	printf(_("  -q, --quiet            do not print any output, except for errors\n"));
 	printf(_("  -r, --rmgr=RMGR        only show records generated by resource manager RMGR;\n"
@@ -806,7 +844,10 @@ main(int argc, char **argv)
 	XLogRecord *record;
 	XLogRecPtr	first_record;
 	char	   *waldir = NULL;
+	char	   *walpath = NULL;
 	char	   *errormsg;
+	bool		is_archive = false;
+	pg_compress_algorithm compression;
 
 	static struct option long_options[] = {
 		{"bkp-details", no_argument, NULL, 'b'},
@@ -938,7 +979,7 @@ main(int argc, char **argv)
 				}
 				break;
 			case 'p':
-				waldir = pg_strdup(optarg);
+				walpath = pg_strdup(optarg);
 				break;
 			case 'q':
 				config.quiet = true;
@@ -1102,10 +1143,27 @@ main(int argc, char **argv)
 		goto bad_argument;
 	}
 
-	if (waldir != NULL)
+	if (walpath != NULL)
 	{
+		/* validate path points to tar archive */
+		if (is_archive_file(walpath, &compression))
+		{
+			char	   *fname = NULL;
+
+			split_path(walpath, &waldir, &fname);
+
+			/*
+			 * A NULL WAL directory indicates that the archive file is located
+			 * in the current working directory of the pg_waldump execution
+			 */
+			if (waldir == NULL)
+				waldir = pg_strdup(".");
+
+			private.archive_name = fname;
+			is_archive = true;
+		}
 		/* validate path points to directory */
-		if (!verify_directory(waldir))
+		else if (!verify_directory(walpath))
 		{
 			pg_log_error("could not open directory \"%s\": %m", waldir);
 			goto bad_argument;
@@ -1123,6 +1181,17 @@ main(int argc, char **argv)
 		int			fd;
 		XLogSegNo	segno;
 
+		/*
+		 * If a tar archive is passed using the --path option, all other
+		 * arguments become unnecessary.
+		 */
+		if (is_archive)
+		{
+			pg_log_error("unnecessary command-line arguments specified with tar archive (first is \"%s\")",
+						 argv[optind]);
+			goto bad_argument;
+		}
+
 		split_path(argv[optind], &directory, &fname);
 
 		if (waldir == NULL && directory != NULL)
@@ -1133,69 +1202,78 @@ main(int argc, char **argv)
 				pg_fatal("could not open directory \"%s\": %m", waldir);
 		}
 
-		waldir = identify_target_directory(waldir, fname);
-		fd = open_file_in_directory(waldir, fname);
-		if (fd < 0)
-			pg_fatal("could not open file \"%s\"", fname);
-		close(fd);
-
-		/* parse position from file */
-		XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
-
-		if (!XLogRecPtrIsValid(private.startptr))
-			XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
-		else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+		if (fname != NULL && is_archive_file(fname, &compression))
 		{
-			pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.startptr),
-						 fname);
-			goto bad_argument;
+			waldir = walpath ? pg_strdup(walpath) : pg_strdup(".");
+			private.archive_name = fname;
+			is_archive = true;
 		}
-
-		/* no second file specified, set end position */
-		if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
-			XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
-
-		/* parse ENDSEG if passed */
-		if (optind + 1 < argc)
+		else
 		{
-			XLogSegNo	endsegno;
-
-			/* ignore directory, already have that */
-			split_path(argv[optind + 1], &directory, &fname);
-
+			waldir = identify_target_directory(waldir, fname);
 			fd = open_file_in_directory(waldir, fname);
 			if (fd < 0)
 				pg_fatal("could not open file \"%s\"", fname);
 			close(fd);
 
 			/* parse position from file */
-			XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+			XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
 
-			if (endsegno < segno)
-				pg_fatal("ENDSEG %s is before STARTSEG %s",
-						 argv[optind + 1], argv[optind]);
+			if (!XLogRecPtrIsValid(private.startptr))
+				XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
+			else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+			{
+				pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.startptr),
+							 fname);
+				goto bad_argument;
+			}
 
-			if (!XLogRecPtrIsValid(private.endptr))
-				XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
-										private.endptr);
+			/* no second file specified, set end position */
+			if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
+				XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
 
-			/* set segno to endsegno for check of --end */
-			segno = endsegno;
-		}
+			/* parse ENDSEG if passed */
+			if (optind + 1 < argc)
+			{
+				XLogSegNo	endsegno;
 
+				/* ignore directory, already have that */
+				split_path(argv[optind + 1], &directory, &fname);
 
-		if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
-			private.endptr != (segno + 1) * WalSegSz)
-		{
-			pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.endptr),
-						 argv[argc - 1]);
-			goto bad_argument;
+				fd = open_file_in_directory(waldir, fname);
+				if (fd < 0)
+					pg_fatal("could not open file \"%s\"", fname);
+				close(fd);
+
+				/* parse position from file */
+				XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+
+				if (endsegno < segno)
+					pg_fatal("ENDSEG %s is before STARTSEG %s",
+							 argv[optind + 1], argv[optind]);
+
+				if (!XLogRecPtrIsValid(private.endptr))
+					XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
+											private.endptr);
+
+				/* set segno to endsegno for check of --end */
+				segno = endsegno;
+			}
+
+
+			if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
+				private.endptr != (segno + 1) * WalSegSz)
+			{
+				pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.endptr),
+							 argv[argc - 1]);
+				goto bad_argument;
+			}
 		}
 	}
-	else
-		waldir = identify_target_directory(waldir, NULL);
+	else if (!is_archive)
+		waldir = identify_target_directory(walpath, NULL);
 
 	/* we don't know what to print */
 	if (!XLogRecPtrIsValid(private.startptr))
@@ -1207,12 +1285,30 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
-	xlogreader_state =
-		XLogReaderAllocate(WalSegSz, waldir,
-						   XL_ROUTINE(.page_read = WALDumpReadPage,
-									  .segment_open = WALDumpOpenSegment,
-									  .segment_close = WALDumpCloseSegment),
-						   &private);
+	if (is_archive)
+	{
+		/* Set up for reading tar file */
+		init_archive_reader(&private, waldir, compression);
+
+		/* Routine to decode WAL files in tar archive */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = TarWALDumpReadPage,
+										  .segment_open = TarWALDumpOpenSegment,
+										  .segment_close = TarWALDumpCloseSegment),
+							   &private);
+	}
+	else
+	{
+		/* Routine to decode WAL files */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = WALDumpReadPage,
+										  .segment_open = WALDumpOpenSegment,
+										  .segment_close = WALDumpCloseSegment),
+							   &private);
+	}
+
 	if (!xlogreader_state)
 		pg_fatal("out of memory while allocating a WAL reading processor");
 
@@ -1321,6 +1417,9 @@ main(int argc, char **argv)
 
 	XLogReaderFree(xlogreader_state);
 
+	if (is_archive)
+		free_archive_reader(&private);
+
 	return EXIT_SUCCESS;
 
 bad_argument:
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 9e62b64ead5..54758c3548a 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -12,9 +12,13 @@
 #define PG_WALDUMP_H
 
 #include "access/xlogdefs.h"
+#include "fe_utils/astreamer.h"
 
 extern int	WalSegSz;
 
+/* Forward declaration */
+struct ArchivedWALEntry;
+
 /* Contains the necessary information to drive WAL decoding */
 typedef struct XLogDumpPrivate
 {
@@ -22,6 +26,36 @@ typedef struct XLogDumpPrivate
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	bool		endptr_reached;
+
+	/* Fields required to read WAL from archive */
+	char	   *archive_name;	/* Tar archive name */
+	int			archive_fd;		/* File descriptor for the open tar file */
+
+	astreamer  *archive_streamer;
+
+	/* What the archive streamer is currently reading */
+	struct ArchivedWALEntry *cur_wal;
+
+	/*
+	 * Although these values can be easily derived from startptr and endptr,
+	 * doing so repeatedly for each archived member would be inefficient, as
+	 * it would involve recalculating and filtering out irrelevant WAL
+	 * segments.
+	 */
+	XLogSegNo	startSegNo;
+	XLogSegNo	endSegNo;
 } XLogDumpPrivate;
 
-#endif		/* end of PG_WALDUMP_H */
+extern int	open_file_in_directory(const char *directory, const char *fname);
+
+extern bool is_archive_file(const char *fname,
+							pg_compress_algorithm *compression);
+extern void init_archive_reader(XLogDumpPrivate *privateInfo,
+								const char *waldir,
+								pg_compress_algorithm compression);
+extern void free_archive_reader(XLogDumpPrivate *privateInfo);
+extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
+								  XLogRecPtr targetPagePtr,
+								  Size count, char *readBuff);
+
+#endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 1b712e8d74d..443126a9ce6 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -3,10 +3,13 @@
 
 use strict;
 use warnings FATAL => 'all';
+use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
 
+my $tar = $ENV{TAR};
+
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
 program_options_handling_ok('pg_waldump');
@@ -235,7 +238,7 @@ command_like(
 sub test_pg_waldump
 {
 	local $Test::Builder::Level = $Test::Builder::Level + 1;
-	my @opts = @_;
+	my ($path, @opts) = @_;
 
 	my ($stdout, $stderr);
 
@@ -243,6 +246,7 @@ sub test_pg_waldump
 		'pg_waldump',
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
+		'--path' => $path,
 		@opts
 	  ],
 	  '>' => \$stdout,
@@ -254,11 +258,50 @@ sub test_pg_waldump
 	return @lines;
 }
 
-my @lines;
+# Create a tar archive, sorting the file order
+sub generate_archive
+{
+	my ($archive, $directory, $compression_flags) = @_;
+
+	my @files;
+	opendir my $dh, $directory or die "opendir: $!";
+	while (my $entry = readdir $dh) {
+		# Skip '.' and '..'
+		next if $entry eq '.' || $entry eq '..';
+		push @files, $entry;
+	}
+	closedir $dh;
+
+	@files = sort @files;
+
+	# move into the WAL directory before archiving files
+	my $cwd = getcwd;
+	chdir($directory) || die "chdir: $!";
+	command_ok([$tar, $compression_flags, $archive, @files]);
+	chdir($cwd) || die "chdir: $!";
+}
+
+my $tmp_dir = PostgreSQL::Test::Utils::tempdir_short();
 
 my @scenario = (
 	{
-		'path' => $node->data_dir
+		'path' => $node->data_dir,
+		'is_archive' => 0,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar",
+		'compression_method' => 'none',
+		'compression_flags' => '-cf',
+		'is_archive' => 1,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar.gz",
+		'compression_method' => 'gzip',
+		'compression_flags' => '-czf',
+		'is_archive' => 1,
+		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
 	});
 
 for my $scenario (@scenario)
@@ -267,6 +310,19 @@ for my $scenario (@scenario)
 
 	SKIP:
 	{
+		skip "tar command is not available", 3
+		  if !defined $tar;
+		skip "$scenario->{'compression_method'} compression not supported by this build", 3
+		  if !$scenario->{'enabled'} && $scenario->{'is_archive'};
+
+		  # create pg_wal archive
+		  if ($scenario->{'is_archive'})
+		  {
+			  generate_archive($path,
+				  $node->data_dir . '/pg_wal',
+				  $scenario->{'compression_flags'});
+		  }
+
 		command_fails_like(
 			[ 'pg_waldump', '--path' => $path ],
 			qr/error: no start WAL location given/,
@@ -298,38 +354,42 @@ for my $scenario (@scenario)
 			qr/error: error in WAL record at/,
 			'errors are shown with --quiet');
 
-		@lines = test_pg_waldump('--path' => $path);
+		my @lines;
+		@lines = test_pg_waldump($path);
 		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		@lines = test_pg_waldump($path, '--limit' => 6);
 		is(@lines, 6, 'limit option observed');
 
-		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		@lines = test_pg_waldump($path, '--fullpage');
 		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats');
+		@lines = test_pg_waldump($path, '--stats');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		@lines = test_pg_waldump($path, '--stats=record');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		@lines = test_pg_waldump($path, '--rmgr' => 'Btree');
 		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		@lines = test_pg_waldump($path, '--fork' => 'init');
 		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
 		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
 			0, 'only lines for selected relation');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
 			'--block' => 1);
 		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+
+		# Cleanup.
+		unlink $path if $scenario->{'is_archive'};
 	}
 }
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 23bce72ae64..0c8d6bfa3e1 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -139,6 +139,8 @@ ArchiveOpts
 ArchiveShutdownCB
 ArchiveStartupCB
 ArchiveStreamState
+ArchivedWALEntry
+ArchivedWAL_hash
 ArchiverOutput
 ArchiverStage
 ArrayAnalyzeExtraData
@@ -3461,6 +3463,7 @@ astreamer_recovery_injector
 astreamer_tar_archiver
 astreamer_tar_parser
 astreamer_verify
+astreamer_waldump
 astreamer_zstd_frame
 auth_password_hook_typ
 autovac_table
-- 
2.47.1

From 7422ff4700b7493eef3c9097e86f99da5aaeeac3 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 6 Nov 2025 13:48:33 +0530
Subject: [PATCH v6 5/8] pg_waldump: Remove the restriction on the order of
 archived WAL files.

With previous patch, pg_waldump would stop decoding if WAL files were
not in the required sequence. With this patch, decoding will now
continue.  Any WAL file that is out of order will be written to a
temporary location, from which it will be read later. Once a temporary
file has been read, it will be removed.
---
 src/bin/pg_waldump/archive_waldump.c | 207 +++++++++++++++++++++++++--
 src/bin/pg_waldump/pg_waldump.c      |  41 +++++-
 src/bin/pg_waldump/pg_waldump.h      |   4 +
 src/bin/pg_waldump/t/001_basic.pl    |   3 +-
 4 files changed, 243 insertions(+), 12 deletions(-)

diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
index 2830c89a7be..7c8f17ba135 100644
--- a/src/bin/pg_waldump/archive_waldump.c
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -17,6 +17,7 @@
 #include <unistd.h>
 
 #include "access/xlog_internal.h"
+#include "common/file_perm.h"
 #include "common/hashfn.h"
 #include "common/logging.h"
 #include "fe_utils/simple_list.h"
@@ -27,6 +28,11 @@
  */
 #define READ_CHUNK_SIZE				(128 * 1024)
 
+#define TEMP_FILE_PREFIX "waldump.tmp"
+
+/* Temporary exported WAL file directory */
+static char *TmpWalSegDir = NULL;
+
 /* Structure for storing the WAL segment data from the archive */
 typedef struct ArchivedWALEntry
 {
@@ -65,6 +71,11 @@ typedef struct astreamer_waldump
 static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
 static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
 											   XLogDumpPrivate *privateInfo);
+static void setup_tmpseg_dir(const char *waldir);
+static void cleanup_tmpseg_dir_atexit(void);
+
+static FILE *prepare_tmp_write(XLogSegNo segno);
+static void perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file);
 
 static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
 static void astreamer_waldump_content(astreamer *streamer,
@@ -120,10 +131,11 @@ is_archive_file(const char *fname, pg_compress_algorithm *compression)
 }
 
 /*
- * Initializes the tar archive reader to read WAL files from the archive,
- * creates a hash table to store them, performs quick existence checks for WAL
- * entries in the archive and retrieves the WAL segment size, and sets up
- * filtering criteria for relevant entries.
+ * Initializes the tar archive reader, creates a hash table for WAL entries,
+ * checks for existing valid WAL segments in the archive file and retrieves the
+ * segment size, and sets up filters for relevant entries. It also configures a
+ * temporary directory for out-of-order WAL data and registers an exit callback
+ * to clean up temporary files.
  */
 void
 init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
@@ -194,6 +206,13 @@ init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
 	 */
 	XLByteToSeg(privateInfo->startptr, privateInfo->startSegNo, WalSegSz);
 	XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+
+	/*
+	 * Setup temporary directory to store WAL segments and set up an exit
+	 * callback to remove it upon completion.
+	 */
+	setup_tmpseg_dir(waldir);
+	atexit(cleanup_tmpseg_dir_atexit);
 }
 
 /*
@@ -362,13 +381,16 @@ read_archive_file(XLogDumpPrivate *privateInfo, Size count)
 /*
  * Returns the archived WAL entry from the hash table if it exists. Otherwise,
  * it invokes the routine to read the archived file and retrieve the entry if
- * it is not already in hash table.
+ * it is not already present in the hash table. If the archive streamer happens
+ * to be reading a WAL from archive file that is not currently needed, that WAL
+ * data is written to a temporary file.
  */
 static ArchivedWALEntry *
 get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 {
 	ArchivedWALEntry *entry = NULL;
 	char		fname[MAXFNAMELEN];
+	FILE	   *write_fp = NULL;
 
 	/* Search hash table */
 	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
@@ -411,11 +433,32 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 			continue;
 		}
 
-		/* WAL segments must be archived in order */
-		pg_log_error("WAL files are not archived in sequential order");
-		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
-							segno, entry->segno);
-		exit(1);
+		/*
+		 * Archive streamer is currently reading a file that isn't the one
+		 * asked for, but it's required for a future feature. It should be
+		 * written to a temporary location for retrieval when needed.
+		 */
+
+		/* Create a temporary file if one does not already exist */
+		if (!entry->tmpseg_exists)
+		{
+			write_fp = prepare_tmp_write(entry->segno);
+			entry->tmpseg_exists = true;
+		}
+
+		/* Flush data from the buffer to the file */
+		perform_tmp_write(entry->segno, &entry->buf, write_fp);
+		resetStringInfo(&entry->buf);
+
+		/*
+		 * The change in the current segment entry indicates that the reading
+		 * of this file has ended.
+		 */
+		if (entry != privateInfo->cur_wal && write_fp != NULL)
+		{
+			fclose(write_fp);
+			write_fp = NULL;
+		}
 	}
 
 	/* Requested WAL segment not found */
@@ -423,6 +466,150 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 	pg_fatal("could not find file \"%s\" in archive", fname);
 }
 
+/*
+ * Set up a temporary directory to temporarily store WAL segments.
+ */
+static void
+setup_tmpseg_dir(const char *waldir)
+{
+	/*
+	 * Use the directory specified by the TEMDIR environment variable. If it's
+	 * not set, use the provided WAL directory to extract WAL file
+	 * temporarily.
+	 */
+	TmpWalSegDir = getenv("TMPDIR") ?
+		pg_strdup(getenv("TMPDIR")) : pg_strdup(waldir);
+	canonicalize_path(TmpWalSegDir);
+}
+
+/*
+ * Removes the temporarily store WAL segments, if any, at exiting.
+ */
+static void
+cleanup_tmpseg_dir_atexit(void)
+{
+	ArchivedWAL_iterator it;
+	ArchivedWALEntry *entry;
+
+	ArchivedWAL_start_iterate(ArchivedWAL_HTAB, &it);
+	while ((entry = ArchivedWAL_iterate(ArchivedWAL_HTAB, &it)) != NULL)
+	{
+		if (entry->tmpseg_exists)
+		{
+			remove_tmp_walseg(entry->segno, false);
+			entry->tmpseg_exists = false;
+		}
+	}
+}
+
+/*
+ * Generate the temporary WAL file path.
+ *
+ * Note that the caller is responsible to pfree it.
+ */
+char *
+get_tmp_walseg_path(XLogSegNo segno)
+{
+	char	   *fpath = (char *) palloc(MAXPGPATH);
+
+	snprintf(fpath, MAXPGPATH, "%s/%s.%08X%08X",
+			 TmpWalSegDir,
+			 TEMP_FILE_PREFIX,
+			 (uint32) (segno / XLogSegmentsPerXLogId(WalSegSz)),
+			 (uint32) (segno % XLogSegmentsPerXLogId(WalSegSz)));
+
+	return fpath;
+}
+
+/*
+ * Routine to check whether a temporary file exists for the corresponding WAL
+ * segment number.
+ */
+bool
+tmp_walseg_exists(XLogSegNo segno)
+{
+	ArchivedWALEntry *entry;
+
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry == NULL)
+		return false;
+
+	return entry->tmpseg_exists;
+}
+
+/*
+ * Create an empty placeholder file and return its handle.
+ */
+static FILE *
+prepare_tmp_write(XLogSegNo segno)
+{
+	FILE	   *file;
+	char	   *fpath;
+
+	fpath = get_tmp_walseg_path(segno);
+
+	/* Create an empty placeholder */
+	file = fopen(fpath, PG_BINARY_W);
+	if (file == NULL)
+		pg_fatal("could not create file \"%s\": %m", fpath);
+
+#ifndef WIN32
+	if (chmod(fpath, pg_file_create_mode))
+		pg_fatal("could not set permissions on file \"%s\": %m",
+				 fpath);
+#endif
+
+	pg_log_debug("temporarily exporting file \"%s\"", fpath);
+	pfree(fpath);
+
+	return file;
+}
+
+/*
+ * Write buffer data to the given file handle.
+ */
+static void
+perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file)
+{
+	Assert(file);
+
+	errno = 0;
+	if (buf->len > 0 && fwrite(buf->data, buf->len, 1, file) != 1)
+	{
+		/*
+		 * If write didn't set errno, assume problem is no disk space
+		 */
+		if (errno == 0)
+			errno = ENOSPC;
+		pg_fatal("could not write to file \"%s\": %m",
+				 get_tmp_walseg_path(segno));
+	}
+}
+
+/*
+ * Remove temporary file
+ */
+void
+remove_tmp_walseg(XLogSegNo segno, bool update_entry)
+{
+	char	   *fpath = get_tmp_walseg_path(segno);
+
+	if (unlink(fpath) == 0)
+		pg_log_debug("removed file \"%s\"", fpath);
+	pfree(fpath);
+
+	/* Update entry if requested */
+	if (update_entry)
+	{
+		ArchivedWALEntry *entry;
+
+		entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+		Assert(entry != NULL);
+		entry->tmpseg_exists = false;
+	}
+}
+
 /*
  * Create an astreamer that can read WAL from tar file.
  */
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 7425d386d0c..a472ef59575 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -466,11 +466,50 @@ TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 {
 	XLogDumpPrivate *private = state->private_data;
 	int			count = required_read_len(private, targetPagePtr, reqLen);
+	XLogSegNo	nextSegNo;
 
 	if (private->endptr_reached)
 		return -1;
 
-	/* Read the WAL page from the archive streamer */
+	/*
+	 * If the target page is in a different segment, first check for the WAL
+	 * segment's physical existence in the temporary directory.
+	 */
+	nextSegNo = state->seg.ws_segno;
+	if (!XLByteInSeg(targetPagePtr, nextSegNo, WalSegSz))
+	{
+		if (state->seg.ws_file >= 0)
+		{
+			close(state->seg.ws_file);
+			state->seg.ws_file = -1;
+
+			/* Remove this file, as it is no longer needed. */
+			remove_tmp_walseg(nextSegNo, true);
+		}
+
+		XLByteToSeg(targetPagePtr, nextSegNo, WalSegSz);
+		state->seg.ws_tli = private->timeline;
+		state->seg.ws_segno = nextSegNo;
+
+		/*
+		 * If the next segment exists, open it and continue reading from there
+		 */
+		if (tmp_walseg_exists(nextSegNo))
+		{
+			char	   *fpath;
+
+			fpath = get_tmp_walseg_path(nextSegNo);
+			state->seg.ws_file = open(fpath, O_RDONLY | PG_BINARY, 0);
+			pfree(fpath);
+		}
+	}
+
+	/* Continue reading from the open WAL segment, if any */
+	if (state->seg.ws_file >= 0)
+		return WALDumpReadPage(state, targetPagePtr, count, targetPtr,
+							   readBuff);
+
+	/* Otherwise, read the WAL page from the archive streamer */
 	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
 }
 
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 54758c3548a..5c1fb1e080a 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -58,4 +58,8 @@ extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
 								  XLogRecPtr targetPagePtr,
 								  Size count, char *readBuff);
 
+extern char *get_tmp_walseg_path(XLogSegNo segno);
+extern bool tmp_walseg_exists(XLogSegNo segno);
+extern void remove_tmp_walseg(XLogSegNo segno, bool update_entry);
+
 #endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 443126a9ce6..d5fa1f6d28d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -7,6 +7,7 @@ use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
+use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
 
@@ -272,7 +273,7 @@ sub generate_archive
 	}
 	closedir $dh;
 
-	@files = sort @files;
+	@files = shuffle @files;
 
 	# move into the WAL directory before archiving files
 	my $cwd = getcwd;
-- 
2.47.1

From d89200d65e3a9cc2e8737ebea850e63c41a6e0e6 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 14:47:43 +0530
Subject: [PATCH v6 6/8] pg_verifybackup: Delay default WAL directory
 preparation.

We are not sure whether to parse WAL from a directory or an archive
until the backup format is known. Therefore, we delay preparing the
default WAL directory until the point of parsing. This delay is
harmless, as the WAL directory is not used elsewhere.
---
 src/bin/pg_verifybackup/pg_verifybackup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 8d5befa947f..a502e795b2e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -285,10 +285,6 @@ main(int argc, char **argv)
 		manifest_path = psprintf("%s/backup_manifest",
 								 context.backup_directory);
 
-	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
-
 	/*
 	 * Try to read the manifest. We treat any errors encountered while parsing
 	 * the manifest as fatal; there doesn't seem to be much point in trying to
@@ -368,6 +364,10 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
+	/* By default, look for the WAL in the backup directory, too. */
+	if (wal_directory == NULL)
+		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
-- 
2.47.1

From c9de01ace1794801aa189aebff923a68e93af893 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 24 Jul 2025 16:37:43 +0530
Subject: [PATCH v6 7/8] pg_verifybackup: Rename the wal-directory switch to
 wal-path

With previous patches to pg_waldump can now decode WAL directly from
tar files.  This means you'll be able to specify a tar archive path
instead of a traditional WAL directory.

To keep things consistent and more versatile, we should also
generalize the input switch for pg_verifybackup. It should accept
either a directory or a tar file path that contains WALs. This change
will also aligning it with the existing manifest-path switch naming.
---
 doc/src/sgml/ref/pg_verifybackup.sgml     |  2 +-
 src/bin/pg_verifybackup/pg_verifybackup.c | 22 +++++++++++-----------
 src/bin/pg_verifybackup/po/de.po          |  4 ++--
 src/bin/pg_verifybackup/po/el.po          |  4 ++--
 src/bin/pg_verifybackup/po/es.po          |  4 ++--
 src/bin/pg_verifybackup/po/fr.po          |  4 ++--
 src/bin/pg_verifybackup/po/it.po          |  4 ++--
 src/bin/pg_verifybackup/po/ja.po          |  4 ++--
 src/bin/pg_verifybackup/po/ka.po          |  4 ++--
 src/bin/pg_verifybackup/po/ko.po          |  4 ++--
 src/bin/pg_verifybackup/po/ru.po          |  4 ++--
 src/bin/pg_verifybackup/po/sv.po          |  4 ++--
 src/bin/pg_verifybackup/po/uk.po          |  4 ++--
 src/bin/pg_verifybackup/po/zh_CN.po       |  4 ++--
 src/bin/pg_verifybackup/po/zh_TW.po       |  4 ++--
 src/bin/pg_verifybackup/t/007_wal.pl      |  4 ++--
 16 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index 61c12975e4a..e9b8bfd51b1 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -261,7 +261,7 @@ PostgreSQL documentation
 
      <varlistentry>
       <term><option>-w <replaceable class="parameter">path</replaceable></option></term>
-      <term><option>--wal-directory=<replaceable class="parameter">path</replaceable></option></term>
+      <term><option>--wal-path=<replaceable class="parameter">path</replaceable></option></term>
       <listitem>
        <para>
         Try to parse WAL files stored in the specified directory, rather than
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index a502e795b2e..9fcd6be004e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -93,7 +93,7 @@ static void verify_file_checksum(verifier_context *context,
 								 uint8 *buffer);
 static void parse_required_wal(verifier_context *context,
 							   char *pg_waldump_path,
-							   char *wal_directory);
+							   char *wal_path);
 static astreamer *create_archive_verifier(verifier_context *context,
 										  char *archive_name,
 										  Oid tblspc_oid,
@@ -126,7 +126,7 @@ main(int argc, char **argv)
 		{"progress", no_argument, NULL, 'P'},
 		{"quiet", no_argument, NULL, 'q'},
 		{"skip-checksums", no_argument, NULL, 's'},
-		{"wal-directory", required_argument, NULL, 'w'},
+		{"wal-path", required_argument, NULL, 'w'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -135,7 +135,7 @@ main(int argc, char **argv)
 	char	   *manifest_path = NULL;
 	bool		no_parse_wal = false;
 	bool		quiet = false;
-	char	   *wal_directory = NULL;
+	char	   *wal_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -221,8 +221,8 @@ main(int argc, char **argv)
 				context.skip_checksums = true;
 				break;
 			case 'w':
-				wal_directory = pstrdup(optarg);
-				canonicalize_path(wal_directory);
+				wal_path = pstrdup(optarg);
+				canonicalize_path(wal_path);
 				break;
 			default:
 				/* getopt_long already emitted a complaint */
@@ -365,15 +365,15 @@ main(int argc, char **argv)
 		verify_backup_checksums(&context);
 
 	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+	if (wal_path == NULL)
+		wal_path = psprintf("%s/pg_wal", context.backup_directory);
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
 	 */
 	if (!no_parse_wal)
-		parse_required_wal(&context, pg_waldump_path, wal_directory);
+		parse_required_wal(&context, pg_waldump_path, wal_path);
 
 	/*
 	 * If everything looks OK, tell the user this, unless we were asked to
@@ -1198,7 +1198,7 @@ verify_file_checksum(verifier_context *context, manifest_file *m,
  */
 static void
 parse_required_wal(verifier_context *context, char *pg_waldump_path,
-				   char *wal_directory)
+				   char *wal_path)
 {
 	manifest_data *manifest = context->manifest;
 	manifest_wal_range *this_wal_range = manifest->first_wal_range;
@@ -1208,7 +1208,7 @@ parse_required_wal(verifier_context *context, char *pg_waldump_path,
 		char	   *pg_waldump_cmd;
 
 		pg_waldump_cmd = psprintf("\"%s\" --quiet --path=\"%s\" --timeline=%u --start=%X/%08X --end=%X/%08X\n",
-								  pg_waldump_path, wal_directory, this_wal_range->tli,
+								  pg_waldump_path, wal_path, this_wal_range->tli,
 								  LSN_FORMAT_ARGS(this_wal_range->start_lsn),
 								  LSN_FORMAT_ARGS(this_wal_range->end_lsn));
 		fflush(NULL);
@@ -1376,7 +1376,7 @@ usage(void)
 	printf(_("  -P, --progress              show progress information\n"));
 	printf(_("  -q, --quiet                 do not print any output, except for errors\n"));
 	printf(_("  -s, --skip-checksums        skip checksum verification\n"));
-	printf(_("  -w, --wal-directory=PATH    use specified path for WAL files\n"));
+	printf(_("  -w, --wal-path=PATH         use specified path for WAL files\n"));
 	printf(_("  -V, --version               output version information, then exit\n"));
 	printf(_("  -?, --help                  show this help, then exit\n"));
 	printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
diff --git a/src/bin/pg_verifybackup/po/de.po b/src/bin/pg_verifybackup/po/de.po
index a9e24931100..9b5cd5898cf 100644
--- a/src/bin/pg_verifybackup/po/de.po
+++ b/src/bin/pg_verifybackup/po/de.po
@@ -785,8 +785,8 @@ msgstr "  -s, --skip-checksums        Überprüfung der Prüfsummen überspringe
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/el.po b/src/bin/pg_verifybackup/po/el.po
index 3e3f20c67c5..81442f51c17 100644
--- a/src/bin/pg_verifybackup/po/el.po
+++ b/src/bin/pg_verifybackup/po/el.po
@@ -494,8 +494,8 @@ msgstr "  -s, --skip-checksums        παράκαμψε την επαλήθευ
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/es.po b/src/bin/pg_verifybackup/po/es.po
index 0cb958f3448..7f729fa35ba 100644
--- a/src/bin/pg_verifybackup/po/es.po
+++ b/src/bin/pg_verifybackup/po/es.po
@@ -495,8 +495,8 @@ msgstr "  -s, --skip-checksums        omitir la verificación de la suma de comp
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    utilizar la ruta especificada para los archivos WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    utilizar la ruta especificada para los archivos WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/fr.po b/src/bin/pg_verifybackup/po/fr.po
index da8c72f6427..09937966fa7 100644
--- a/src/bin/pg_verifybackup/po/fr.po
+++ b/src/bin/pg_verifybackup/po/fr.po
@@ -498,8 +498,8 @@ msgstr "  -s, --skip-checksums        ignore la vérification des sommes de cont
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/it.po b/src/bin/pg_verifybackup/po/it.po
index 317b0b71e7f..4da68d0074e 100644
--- a/src/bin/pg_verifybackup/po/it.po
+++ b/src/bin/pg_verifybackup/po/it.po
@@ -472,8 +472,8 @@ msgstr "  -s, --skip-checksums         salta la verifica del checksum\n"
 
 #: pg_verifybackup.c:911
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH     usa il percorso specificato per i file WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH     usa il percorso specificato per i file WAL\n"
 
 #: pg_verifybackup.c:912
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ja.po b/src/bin/pg_verifybackup/po/ja.po
index c910fb236cc..a948959b54f 100644
--- a/src/bin/pg_verifybackup/po/ja.po
+++ b/src/bin/pg_verifybackup/po/ja.po
@@ -672,8 +672,8 @@ msgstr "  -s, --skip-checksums        チェックサム検証をスキップ\n"
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    WALファイルに指定したパスを使用する\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    WALファイルに指定したパスを使用する\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ka.po b/src/bin/pg_verifybackup/po/ka.po
index 982751984c7..ef2799316a8 100644
--- a/src/bin/pg_verifybackup/po/ka.po
+++ b/src/bin/pg_verifybackup/po/ka.po
@@ -784,8 +784,8 @@ msgstr "  -s, --skip-checksums        საკონტროლო ჯამ
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ko.po b/src/bin/pg_verifybackup/po/ko.po
index acdc3da5e02..eaf91ef1e98 100644
--- a/src/bin/pg_verifybackup/po/ko.po
+++ b/src/bin/pg_verifybackup/po/ko.po
@@ -501,8 +501,8 @@ msgstr "  -s, --skip-checksums        체크섬 검사 건너뜀\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=경로    WAL 파일이 있는 경로 지정\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=경로    WAL 파일이 있는 경로 지정\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ru.po b/src/bin/pg_verifybackup/po/ru.po
index 64005feedfd..7fb0e5ab1f6 100644
--- a/src/bin/pg_verifybackup/po/ru.po
+++ b/src/bin/pg_verifybackup/po/ru.po
@@ -507,9 +507,9 @@ msgstr "  -s, --skip-checksums        пропустить проверку ко
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
 msgstr ""
-"  -w, --wal-directory=ПУТЬ    использовать заданный путь к файлам WAL\n"
+"  -w, --wal-path=ПУТЬ    использовать заданный путь к файлам WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/sv.po b/src/bin/pg_verifybackup/po/sv.po
index 17240feeb5c..97125838e8c 100644
--- a/src/bin/pg_verifybackup/po/sv.po
+++ b/src/bin/pg_verifybackup/po/sv.po
@@ -492,8 +492,8 @@ msgstr "  -s, --skip-checksums        hoppa över verifiering av kontrollsummor\
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=SÖKVÄG  använd denna sökväg till WAL-filer\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=SÖKVÄG  använd denna sökväg till WAL-filer\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/uk.po b/src/bin/pg_verifybackup/po/uk.po
index 034b9764232..63f8041ab38 100644
--- a/src/bin/pg_verifybackup/po/uk.po
+++ b/src/bin/pg_verifybackup/po/uk.po
@@ -484,8 +484,8 @@ msgstr "  -s, --skip-checksums не перевіряти контрольні с
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH використовувати вказаний шлях для файлів WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH використовувати вказаний шлях для файлів WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_CN.po b/src/bin/pg_verifybackup/po/zh_CN.po
index b7d97c8976d..fb6fcae8b82 100644
--- a/src/bin/pg_verifybackup/po/zh_CN.po
+++ b/src/bin/pg_verifybackup/po/zh_CN.po
@@ -465,8 +465,8 @@ msgstr "  -s, --skip-checksums        跳过校验和验证\n"
 
 #: pg_verifybackup.c:919
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    对WAL文件使用指定路径\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    对WAL文件使用指定路径\n"
 
 #: pg_verifybackup.c:920
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_TW.po b/src/bin/pg_verifybackup/po/zh_TW.po
index c1b710b0a36..568f972b0bb 100644
--- a/src/bin/pg_verifybackup/po/zh_TW.po
+++ b/src/bin/pg_verifybackup/po/zh_TW.po
@@ -555,8 +555,8 @@ msgstr "  -s, --skip-checksums        跳過檢查碼驗證\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    用指定的路徑存放 WAL 檔\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    用指定的路徑存放 WAL 檔\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/t/007_wal.pl b/src/bin/pg_verifybackup/t/007_wal.pl
index babc4f0a86b..b07f80719b0 100644
--- a/src/bin/pg_verifybackup/t/007_wal.pl
+++ b/src/bin/pg_verifybackup/t/007_wal.pl
@@ -42,10 +42,10 @@ command_ok([ 'pg_verifybackup', '--no-parse-wal', $backup_path ],
 command_ok(
 	[
 		'pg_verifybackup',
-		'--wal-directory' => $relocated_pg_wal,
+		'--wal-path' => $relocated_pg_wal,
 		$backup_path
 	],
-	'--wal-directory can be used to specify WAL directory');
+	'--wal-path can be used to specify WAL directory');
 
 # Move directory back to original location.
 rename($relocated_pg_wal, $original_pg_wal) || die "rename pg_wal back: $!";
-- 
2.47.1

From b823bc3086f80e869057ccef0c6e8a3f7c664a9a Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 17 Jul 2025 16:39:36 +0530
Subject: [PATCH v6 8/8] pg_verifybackup: enabled WAL parsing for tar-format
 backup

Now that pg_waldump supports decoding from tar archives, we should
leverage this functionality to remove the previous restriction on WAL
parsing for tar-backed formats.
---
 doc/src/sgml/ref/pg_verifybackup.sgml         |  5 +-
 src/bin/pg_verifybackup/pg_verifybackup.c     | 66 +++++++++++++------
 src/bin/pg_verifybackup/t/002_algorithm.pl    |  4 --
 src/bin/pg_verifybackup/t/003_corruption.pl   |  4 +-
 src/bin/pg_verifybackup/t/008_untar.pl        |  5 +-
 src/bin/pg_verifybackup/t/010_client_untar.pl |  5 +-
 6 files changed, 50 insertions(+), 39 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index e9b8bfd51b1..16b50b5a4df 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -36,10 +36,7 @@ PostgreSQL documentation
    <literal>backup_manifest</literal> generated by the server at the time
    of the backup. The backup may be stored either in the "plain" or the "tar"
    format; this includes tar-format backups compressed with any algorithm
-   supported by <application>pg_basebackup</application>. However, at present,
-   <literal>WAL</literal> verification is supported only for plain-format
-   backups. Therefore, if the backup is stored in tar-format, the
-   <literal>-n, --no-parse-wal</literal> option should be used.
+   supported by <application>pg_basebackup</application>.
   </para>
 
   <para>
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 9fcd6be004e..6915fc7f28e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -74,7 +74,9 @@ pg_noreturn static void report_manifest_error(JsonManifestParseContext *context,
 											  const char *fmt,...)
 			pg_attribute_printf(2, 3);
 
-static void verify_tar_backup(verifier_context *context, DIR *dir);
+static void verify_tar_backup(verifier_context *context, DIR *dir,
+							  char **base_archive_path,
+							  char **wal_archive_path);
 static void verify_plain_backup_directory(verifier_context *context,
 										  char *relpath, char *fullpath,
 										  DIR *dir);
@@ -83,7 +85,9 @@ static void verify_plain_backup_file(verifier_context *context, char *relpath,
 static void verify_control_file(const char *controlpath,
 								uint64 manifest_system_identifier);
 static void precheck_tar_backup_file(verifier_context *context, char *relpath,
-									 char *fullpath, SimplePtrList *tarfiles);
+									 char *fullpath, SimplePtrList *tarfiles,
+									 char **base_archive_path,
+									 char **wal_archive_path);
 static void verify_tar_file(verifier_context *context, char *relpath,
 							char *fullpath, astreamer *streamer);
 static void report_extra_backup_files(verifier_context *context);
@@ -136,6 +140,8 @@ main(int argc, char **argv)
 	bool		no_parse_wal = false;
 	bool		quiet = false;
 	char	   *wal_path = NULL;
+	char	   *base_archive_path = NULL;
+	char	   *wal_archive_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -327,17 +333,6 @@ main(int argc, char **argv)
 		pfree(path);
 	}
 
-	/*
-	 * XXX: In the future, we should consider enhancing pg_waldump to read WAL
-	 * files from an archive.
-	 */
-	if (!no_parse_wal && context.format == 't')
-	{
-		pg_log_error("pg_waldump cannot read tar files");
-		pg_log_error_hint("You must use -n/--no-parse-wal when verifying a tar-format backup.");
-		exit(1);
-	}
-
 	/*
 	 * Perform the appropriate type of verification appropriate based on the
 	 * backup format. This will close 'dir'.
@@ -346,7 +341,7 @@ main(int argc, char **argv)
 		verify_plain_backup_directory(&context, NULL, context.backup_directory,
 									  dir);
 	else
-		verify_tar_backup(&context, dir);
+		verify_tar_backup(&context, dir, &base_archive_path, &wal_archive_path);
 
 	/*
 	 * The "matched" flag should now be set on every entry in the hash table.
@@ -364,9 +359,28 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
-	/* By default, look for the WAL in the backup directory, too. */
+	/*
+	 * By default, WAL files are expected to be found in the backup directory
+	 * for plain-format backups. In the case of tar-format backups, if a
+	 * separate WAL archive is not found, the WAL files are most likely
+	 * included within the main data directory archive.
+	 */
 	if (wal_path == NULL)
-		wal_path = psprintf("%s/pg_wal", context.backup_directory);
+	{
+		if (context.format == 'p')
+			wal_path = psprintf("%s/pg_wal", context.backup_directory);
+		else if (wal_archive_path)
+			wal_path = wal_archive_path;
+		else if (base_archive_path)
+			wal_path = base_archive_path;
+		else
+		{
+			pg_log_error("wal archive not found");
+			pg_log_error_hint("Specify the correct path using the option -w/--wal-path."
+							  "Or you must use -n/--no-parse-wal when verifying a tar-format backup.");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
@@ -787,7 +801,8 @@ verify_control_file(const char *controlpath, uint64 manifest_system_identifier)
  * close when we're done with it.
  */
 static void
-verify_tar_backup(verifier_context *context, DIR *dir)
+verify_tar_backup(verifier_context *context, DIR *dir, char **base_archive_path,
+				  char **wal_archive_path)
 {
 	struct dirent *dirent;
 	SimplePtrList tarfiles = {NULL, NULL};
@@ -816,7 +831,8 @@ verify_tar_backup(verifier_context *context, DIR *dir)
 			char	   *fullpath;
 
 			fullpath = psprintf("%s/%s", context->backup_directory, filename);
-			precheck_tar_backup_file(context, filename, fullpath, &tarfiles);
+			precheck_tar_backup_file(context, filename, fullpath, &tarfiles,
+									 base_archive_path, wal_archive_path);
 			pfree(fullpath);
 		}
 	}
@@ -875,11 +891,13 @@ verify_tar_backup(verifier_context *context, DIR *dir)
  *
  * The arguments to this function are mostly the same as the
  * verify_plain_backup_file. The additional argument outputs a list of valid
- * tar files.
+ * tar files, along with the full paths to the main archive and the WAL
+ * directory archive.
  */
 static void
 precheck_tar_backup_file(verifier_context *context, char *relpath,
-						 char *fullpath, SimplePtrList *tarfiles)
+						 char *fullpath, SimplePtrList *tarfiles,
+						 char **base_archive_path, char **wal_archive_path)
 {
 	struct stat sb;
 	Oid			tblspc_oid = InvalidOid;
@@ -918,9 +936,17 @@ precheck_tar_backup_file(verifier_context *context, char *relpath,
 	 * extension such as .gz, .lz4, or .zst.
 	 */
 	if (strncmp("base", relpath, 4) == 0)
+	{
 		suffix = relpath + 4;
+
+		*base_archive_path = pstrdup(fullpath);
+	}
 	else if (strncmp("pg_wal", relpath, 6) == 0)
+	{
 		suffix = relpath + 6;
+
+		*wal_archive_path = pstrdup(fullpath);
+	}
 	else
 	{
 		/* Expected a <tablespaceoid>.tar file here. */
diff --git a/src/bin/pg_verifybackup/t/002_algorithm.pl b/src/bin/pg_verifybackup/t/002_algorithm.pl
index ae16c11bc4d..4f284a9e828 100644
--- a/src/bin/pg_verifybackup/t/002_algorithm.pl
+++ b/src/bin/pg_verifybackup/t/002_algorithm.pl
@@ -30,10 +30,6 @@ sub test_checksums
 	{
 		# Add switch to get a tar-format backup
 		push @backup, ('--format' => 'tar');
-
-		# Add switch to skip WAL verification, which is not yet supported for
-		# tar-format backups
-		push @verify, ('--no-parse-wal');
 	}
 
 	# A backup with a bogus algorithm should fail.
diff --git a/src/bin/pg_verifybackup/t/003_corruption.pl b/src/bin/pg_verifybackup/t/003_corruption.pl
index 1dd60f709cf..f1ebdbb46b4 100644
--- a/src/bin/pg_verifybackup/t/003_corruption.pl
+++ b/src/bin/pg_verifybackup/t/003_corruption.pl
@@ -193,10 +193,8 @@ for my $scenario (@scenario)
 			command_ok([ $tar, '-cf' => "$tar_backup_path/base.tar", '.' ]);
 			chdir($cwd) || die "chdir: $!";
 
-			# Now check that the backup no longer verifies. We must use -n
-			# here, because pg_waldump can't yet read WAL from a tarfile.
 			command_fails_like(
-				[ 'pg_verifybackup', '--no-parse-wal', $tar_backup_path ],
+				[ 'pg_verifybackup', $tar_backup_path ],
 				$scenario->{'fails_like'},
 				"corrupt backup fails verification: $name");
 
diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index bc3d6b352ad..09079a94fee 100644
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -47,7 +47,6 @@ my $tsoid = $primary->safe_psql(
 		SELECT oid FROM pg_tablespace WHERE spcname = 'regress_ts1'));
 
 my $backup_path = $primary->backup_dir . '/server-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -123,14 +122,12 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
 		rmtree($backup_path);
-		rmtree($extract_path);
 	}
 }
 
diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index b62faeb5acf..5b0e76ee69d 100644
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -32,7 +32,6 @@ print $jf $junk_data;
 close $jf;
 
 my $backup_path = $primary->backup_dir . '/client-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -137,13 +136,11 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
-		rmtree($extract_path);
 		rmtree($backup_path);
 	}
 }
-- 
2.47.1

From b09abd6a9fc5493a71285a36417bcc18ac017985 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 6 Nov 2025 13:48:33 +0530
Subject: [PATCH v7 5/8] pg_waldump: Remove the restriction on the order of
 archived WAL files.

With previous patch, pg_waldump would stop decoding if WAL files were
not in the required sequence. With this patch, decoding will now
continue.  Any WAL file that is out of order will be written to a
temporary location, from which it will be read later. Once a temporary
file has been read, it will be removed.
---
 src/bin/pg_waldump/archive_waldump.c | 207 +++++++++++++++++++++++++--
 src/bin/pg_waldump/pg_waldump.c      |  41 +++++-
 src/bin/pg_waldump/pg_waldump.h      |   4 +
 src/bin/pg_waldump/t/001_basic.pl    |   3 +-
 4 files changed, 243 insertions(+), 12 deletions(-)

diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
index 61d6782f9b7..6f87c1ab4a4 100644
--- a/src/bin/pg_waldump/archive_waldump.c
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -17,6 +17,7 @@
 #include <unistd.h>
 
 #include "access/xlog_internal.h"
+#include "common/file_perm.h"
 #include "common/hashfn.h"
 #include "common/logging.h"
 #include "fe_utils/simple_list.h"
@@ -27,6 +28,11 @@
  */
 #define READ_CHUNK_SIZE				(128 * 1024)
 
+#define TEMP_FILE_PREFIX "waldump.tmp"
+
+/* Temporary exported WAL file directory */
+static char *TmpWalSegDir = NULL;
+
 /* Structure for storing the WAL segment data from the archive */
 typedef struct ArchivedWALEntry
 {
@@ -65,6 +71,11 @@ typedef struct astreamer_waldump
 static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
 static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
 											   XLogDumpPrivate *privateInfo);
+static void setup_tmpseg_dir(const char *waldir);
+static void cleanup_tmpseg_dir_atexit(void);
+
+static FILE *prepare_tmp_write(XLogSegNo segno);
+static void perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file);
 
 static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
 static void astreamer_waldump_content(astreamer *streamer,
@@ -120,10 +131,11 @@ is_archive_file(const char *fname, pg_compress_algorithm *compression)
 }
 
 /*
- * Initializes the tar archive reader to read WAL files from the archive,
- * creates a hash table to store them, performs quick existence checks for WAL
- * entries in the archive and retrieves the WAL segment size, and sets up
- * filtering criteria for relevant entries.
+ * Initializes the tar archive reader, creates a hash table for WAL entries,
+ * checks for existing valid WAL segments in the archive file and retrieves the
+ * segment size, and sets up filters for relevant entries. It also configures a
+ * temporary directory for out-of-order WAL data and registers an exit callback
+ * to clean up temporary files.
  */
 void
 init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
@@ -194,6 +206,13 @@ init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
 	 */
 	XLByteToSeg(privateInfo->startptr, privateInfo->startSegNo, WalSegSz);
 	XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+
+	/*
+	 * Setup temporary directory to store WAL segments and set up an exit
+	 * callback to remove it upon completion.
+	 */
+	setup_tmpseg_dir(waldir);
+	atexit(cleanup_tmpseg_dir_atexit);
 }
 
 /*
@@ -369,13 +388,16 @@ read_archive_file(XLogDumpPrivate *privateInfo, Size count)
 /*
  * Returns the archived WAL entry from the hash table if it exists. Otherwise,
  * it invokes the routine to read the archived file and retrieve the entry if
- * it is not already in hash table.
+ * it is not already present in the hash table. If the archive streamer happens
+ * to be reading a WAL from archive file that is not currently needed, that WAL
+ * data is written to a temporary file.
  */
 static ArchivedWALEntry *
 get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 {
 	ArchivedWALEntry *entry = NULL;
 	char		fname[MAXFNAMELEN];
+	FILE	   *write_fp = NULL;
 
 	/* Search hash table */
 	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
@@ -418,11 +440,32 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 			continue;
 		}
 
-		/* WAL segments must be archived in order */
-		pg_log_error("WAL files are not archived in sequential order");
-		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
-							segno, entry->segno);
-		exit(1);
+		/*
+		 * Archive streamer is currently reading a file that isn't the one
+		 * asked for, but it's required for a future feature. It should be
+		 * written to a temporary location for retrieval when needed.
+		 */
+
+		/* Create a temporary file if one does not already exist */
+		if (!entry->tmpseg_exists)
+		{
+			write_fp = prepare_tmp_write(entry->segno);
+			entry->tmpseg_exists = true;
+		}
+
+		/* Flush data from the buffer to the file */
+		perform_tmp_write(entry->segno, &entry->buf, write_fp);
+		resetStringInfo(&entry->buf);
+
+		/*
+		 * The change in the current segment entry indicates that the reading
+		 * of this file has ended.
+		 */
+		if (entry != privateInfo->cur_wal && write_fp != NULL)
+		{
+			fclose(write_fp);
+			write_fp = NULL;
+		}
 	}
 
 	/* Requested WAL segment not found */
@@ -430,6 +473,150 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 	pg_fatal("could not find file \"%s\" in archive", fname);
 }
 
+/*
+ * Set up a temporary directory to temporarily store WAL segments.
+ */
+static void
+setup_tmpseg_dir(const char *waldir)
+{
+	/*
+	 * Use the directory specified by the TEMDIR environment variable. If it's
+	 * not set, use the provided WAL directory to extract WAL file
+	 * temporarily.
+	 */
+	TmpWalSegDir = getenv("TMPDIR") ?
+		pg_strdup(getenv("TMPDIR")) : pg_strdup(waldir);
+	canonicalize_path(TmpWalSegDir);
+}
+
+/*
+ * Removes the temporarily store WAL segments, if any, at exiting.
+ */
+static void
+cleanup_tmpseg_dir_atexit(void)
+{
+	ArchivedWAL_iterator it;
+	ArchivedWALEntry *entry;
+
+	ArchivedWAL_start_iterate(ArchivedWAL_HTAB, &it);
+	while ((entry = ArchivedWAL_iterate(ArchivedWAL_HTAB, &it)) != NULL)
+	{
+		if (entry->tmpseg_exists)
+		{
+			remove_tmp_walseg(entry->segno, false);
+			entry->tmpseg_exists = false;
+		}
+	}
+}
+
+/*
+ * Generate the temporary WAL file path.
+ *
+ * Note that the caller is responsible to pfree it.
+ */
+char *
+get_tmp_walseg_path(XLogSegNo segno)
+{
+	char	   *fpath = (char *) palloc(MAXPGPATH);
+
+	snprintf(fpath, MAXPGPATH, "%s/%s.%08X%08X",
+			 TmpWalSegDir,
+			 TEMP_FILE_PREFIX,
+			 (uint32) (segno / XLogSegmentsPerXLogId(WalSegSz)),
+			 (uint32) (segno % XLogSegmentsPerXLogId(WalSegSz)));
+
+	return fpath;
+}
+
+/*
+ * Routine to check whether a temporary file exists for the corresponding WAL
+ * segment number.
+ */
+bool
+tmp_walseg_exists(XLogSegNo segno)
+{
+	ArchivedWALEntry *entry;
+
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry == NULL)
+		return false;
+
+	return entry->tmpseg_exists;
+}
+
+/*
+ * Create an empty placeholder file and return its handle.
+ */
+static FILE *
+prepare_tmp_write(XLogSegNo segno)
+{
+	FILE	   *file;
+	char	   *fpath;
+
+	fpath = get_tmp_walseg_path(segno);
+
+	/* Create an empty placeholder */
+	file = fopen(fpath, PG_BINARY_W);
+	if (file == NULL)
+		pg_fatal("could not create file \"%s\": %m", fpath);
+
+#ifndef WIN32
+	if (chmod(fpath, pg_file_create_mode))
+		pg_fatal("could not set permissions on file \"%s\": %m",
+				 fpath);
+#endif
+
+	pg_log_debug("temporarily exporting file \"%s\"", fpath);
+	pfree(fpath);
+
+	return file;
+}
+
+/*
+ * Write buffer data to the given file handle.
+ */
+static void
+perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file)
+{
+	Assert(file);
+
+	errno = 0;
+	if (buf->len > 0 && fwrite(buf->data, buf->len, 1, file) != 1)
+	{
+		/*
+		 * If write didn't set errno, assume problem is no disk space
+		 */
+		if (errno == 0)
+			errno = ENOSPC;
+		pg_fatal("could not write to file \"%s\": %m",
+				 get_tmp_walseg_path(segno));
+	}
+}
+
+/*
+ * Remove temporary file
+ */
+void
+remove_tmp_walseg(XLogSegNo segno, bool update_entry)
+{
+	char	   *fpath = get_tmp_walseg_path(segno);
+
+	if (unlink(fpath) == 0)
+		pg_log_debug("removed file \"%s\"", fpath);
+	pfree(fpath);
+
+	/* Update entry if requested */
+	if (update_entry)
+	{
+		ArchivedWALEntry *entry;
+
+		entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+		Assert(entry != NULL);
+		entry->tmpseg_exists = false;
+	}
+}
+
 /*
  * Create an astreamer that can read WAL from tar file.
  */
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 02ad141e44a..4c5974a6ae1 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -466,11 +466,50 @@ TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 {
 	XLogDumpPrivate *private = state->private_data;
 	int			count = required_read_len(private, targetPagePtr, reqLen);
+	XLogSegNo	nextSegNo;
 
 	if (private->endptr_reached)
 		return -1;
 
-	/* Read the WAL page from the archive streamer */
+	/*
+	 * If the target page is in a different segment, first check for the WAL
+	 * segment's physical existence in the temporary directory.
+	 */
+	nextSegNo = state->seg.ws_segno;
+	if (!XLByteInSeg(targetPagePtr, nextSegNo, WalSegSz))
+	{
+		if (state->seg.ws_file >= 0)
+		{
+			close(state->seg.ws_file);
+			state->seg.ws_file = -1;
+
+			/* Remove this file, as it is no longer needed. */
+			remove_tmp_walseg(nextSegNo, true);
+		}
+
+		XLByteToSeg(targetPagePtr, nextSegNo, WalSegSz);
+		state->seg.ws_tli = private->timeline;
+		state->seg.ws_segno = nextSegNo;
+
+		/*
+		 * If the next segment exists, open it and continue reading from there
+		 */
+		if (tmp_walseg_exists(nextSegNo))
+		{
+			char	   *fpath;
+
+			fpath = get_tmp_walseg_path(nextSegNo);
+			state->seg.ws_file = open(fpath, O_RDONLY | PG_BINARY, 0);
+			pfree(fpath);
+		}
+	}
+
+	/* Continue reading from the open WAL segment, if any */
+	if (state->seg.ws_file >= 0)
+		return WALDumpReadPage(state, targetPagePtr, count, targetPtr,
+							   readBuff);
+
+	/* Otherwise, read the WAL page from the archive streamer */
 	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
 }
 
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 54758c3548a..5c1fb1e080a 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -58,4 +58,8 @@ extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
 								  XLogRecPtr targetPagePtr,
 								  Size count, char *readBuff);
 
+extern char *get_tmp_walseg_path(XLogSegNo segno);
+extern bool tmp_walseg_exists(XLogSegNo segno);
+extern void remove_tmp_walseg(XLogSegNo segno, bool update_entry);
+
 #endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 443126a9ce6..d5fa1f6d28d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -7,6 +7,7 @@ use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
+use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
 
@@ -272,7 +273,7 @@ sub generate_archive
 	}
 	closedir $dh;
 
-	@files = sort @files;
+	@files = shuffle @files;
 
 	# move into the WAL directory before archiving files
 	my $cwd = getcwd;
-- 
2.47.1

From 7e2523b0891c9911f64c35f736db24e3310e2090 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 14:47:43 +0530
Subject: [PATCH v7 6/8] pg_verifybackup: Delay default WAL directory
 preparation.

We are not sure whether to parse WAL from a directory or an archive
until the backup format is known. Therefore, we delay preparing the
default WAL directory until the point of parsing. This delay is
harmless, as the WAL directory is not used elsewhere.
---
 src/bin/pg_verifybackup/pg_verifybackup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 8d5befa947f..a502e795b2e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -285,10 +285,6 @@ main(int argc, char **argv)
 		manifest_path = psprintf("%s/backup_manifest",
 								 context.backup_directory);
 
-	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
-
 	/*
 	 * Try to read the manifest. We treat any errors encountered while parsing
 	 * the manifest as fatal; there doesn't seem to be much point in trying to
@@ -368,6 +364,10 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
+	/* By default, look for the WAL in the backup directory, too. */
+	if (wal_directory == NULL)
+		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
-- 
2.47.1

From 705fb42e96663b692c5b51650646cf0361b8083e Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 24 Jul 2025 16:37:43 +0530
Subject: [PATCH v7 7/8] pg_verifybackup: Rename the wal-directory switch to
 wal-path

With previous patches to pg_waldump can now decode WAL directly from
tar files.  This means you'll be able to specify a tar archive path
instead of a traditional WAL directory.

To keep things consistent and more versatile, we should also
generalize the input switch for pg_verifybackup. It should accept
either a directory or a tar file path that contains WALs. This change
will also aligning it with the existing manifest-path switch naming.
---
 doc/src/sgml/ref/pg_verifybackup.sgml     |  2 +-
 src/bin/pg_verifybackup/pg_verifybackup.c | 22 +++++++++++-----------
 src/bin/pg_verifybackup/po/de.po          |  4 ++--
 src/bin/pg_verifybackup/po/el.po          |  4 ++--
 src/bin/pg_verifybackup/po/es.po          |  4 ++--
 src/bin/pg_verifybackup/po/fr.po          |  4 ++--
 src/bin/pg_verifybackup/po/it.po          |  4 ++--
 src/bin/pg_verifybackup/po/ja.po          |  4 ++--
 src/bin/pg_verifybackup/po/ka.po          |  4 ++--
 src/bin/pg_verifybackup/po/ko.po          |  4 ++--
 src/bin/pg_verifybackup/po/ru.po          |  4 ++--
 src/bin/pg_verifybackup/po/sv.po          |  4 ++--
 src/bin/pg_verifybackup/po/uk.po          |  4 ++--
 src/bin/pg_verifybackup/po/zh_CN.po       |  4 ++--
 src/bin/pg_verifybackup/po/zh_TW.po       |  4 ++--
 src/bin/pg_verifybackup/t/007_wal.pl      |  4 ++--
 16 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index 61c12975e4a..e9b8bfd51b1 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -261,7 +261,7 @@ PostgreSQL documentation
 
      <varlistentry>
       <term><option>-w <replaceable class="parameter">path</replaceable></option></term>
-      <term><option>--wal-directory=<replaceable class="parameter">path</replaceable></option></term>
+      <term><option>--wal-path=<replaceable class="parameter">path</replaceable></option></term>
       <listitem>
        <para>
         Try to parse WAL files stored in the specified directory, rather than
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index a502e795b2e..9fcd6be004e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -93,7 +93,7 @@ static void verify_file_checksum(verifier_context *context,
 								 uint8 *buffer);
 static void parse_required_wal(verifier_context *context,
 							   char *pg_waldump_path,
-							   char *wal_directory);
+							   char *wal_path);
 static astreamer *create_archive_verifier(verifier_context *context,
 										  char *archive_name,
 										  Oid tblspc_oid,
@@ -126,7 +126,7 @@ main(int argc, char **argv)
 		{"progress", no_argument, NULL, 'P'},
 		{"quiet", no_argument, NULL, 'q'},
 		{"skip-checksums", no_argument, NULL, 's'},
-		{"wal-directory", required_argument, NULL, 'w'},
+		{"wal-path", required_argument, NULL, 'w'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -135,7 +135,7 @@ main(int argc, char **argv)
 	char	   *manifest_path = NULL;
 	bool		no_parse_wal = false;
 	bool		quiet = false;
-	char	   *wal_directory = NULL;
+	char	   *wal_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -221,8 +221,8 @@ main(int argc, char **argv)
 				context.skip_checksums = true;
 				break;
 			case 'w':
-				wal_directory = pstrdup(optarg);
-				canonicalize_path(wal_directory);
+				wal_path = pstrdup(optarg);
+				canonicalize_path(wal_path);
 				break;
 			default:
 				/* getopt_long already emitted a complaint */
@@ -365,15 +365,15 @@ main(int argc, char **argv)
 		verify_backup_checksums(&context);
 
 	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+	if (wal_path == NULL)
+		wal_path = psprintf("%s/pg_wal", context.backup_directory);
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
 	 */
 	if (!no_parse_wal)
-		parse_required_wal(&context, pg_waldump_path, wal_directory);
+		parse_required_wal(&context, pg_waldump_path, wal_path);
 
 	/*
 	 * If everything looks OK, tell the user this, unless we were asked to
@@ -1198,7 +1198,7 @@ verify_file_checksum(verifier_context *context, manifest_file *m,
  */
 static void
 parse_required_wal(verifier_context *context, char *pg_waldump_path,
-				   char *wal_directory)
+				   char *wal_path)
 {
 	manifest_data *manifest = context->manifest;
 	manifest_wal_range *this_wal_range = manifest->first_wal_range;
@@ -1208,7 +1208,7 @@ parse_required_wal(verifier_context *context, char *pg_waldump_path,
 		char	   *pg_waldump_cmd;
 
 		pg_waldump_cmd = psprintf("\"%s\" --quiet --path=\"%s\" --timeline=%u --start=%X/%08X --end=%X/%08X\n",
-								  pg_waldump_path, wal_directory, this_wal_range->tli,
+								  pg_waldump_path, wal_path, this_wal_range->tli,
 								  LSN_FORMAT_ARGS(this_wal_range->start_lsn),
 								  LSN_FORMAT_ARGS(this_wal_range->end_lsn));
 		fflush(NULL);
@@ -1376,7 +1376,7 @@ usage(void)
 	printf(_("  -P, --progress              show progress information\n"));
 	printf(_("  -q, --quiet                 do not print any output, except for errors\n"));
 	printf(_("  -s, --skip-checksums        skip checksum verification\n"));
-	printf(_("  -w, --wal-directory=PATH    use specified path for WAL files\n"));
+	printf(_("  -w, --wal-path=PATH         use specified path for WAL files\n"));
 	printf(_("  -V, --version               output version information, then exit\n"));
 	printf(_("  -?, --help                  show this help, then exit\n"));
 	printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
diff --git a/src/bin/pg_verifybackup/po/de.po b/src/bin/pg_verifybackup/po/de.po
index a9e24931100..9b5cd5898cf 100644
--- a/src/bin/pg_verifybackup/po/de.po
+++ b/src/bin/pg_verifybackup/po/de.po
@@ -785,8 +785,8 @@ msgstr "  -s, --skip-checksums        Überprüfung der Prüfsummen überspringe
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/el.po b/src/bin/pg_verifybackup/po/el.po
index 3e3f20c67c5..81442f51c17 100644
--- a/src/bin/pg_verifybackup/po/el.po
+++ b/src/bin/pg_verifybackup/po/el.po
@@ -494,8 +494,8 @@ msgstr "  -s, --skip-checksums        παράκαμψε την επαλήθευ
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/es.po b/src/bin/pg_verifybackup/po/es.po
index 0cb958f3448..7f729fa35ba 100644
--- a/src/bin/pg_verifybackup/po/es.po
+++ b/src/bin/pg_verifybackup/po/es.po
@@ -495,8 +495,8 @@ msgstr "  -s, --skip-checksums        omitir la verificación de la suma de comp
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    utilizar la ruta especificada para los archivos WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    utilizar la ruta especificada para los archivos WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/fr.po b/src/bin/pg_verifybackup/po/fr.po
index da8c72f6427..09937966fa7 100644
--- a/src/bin/pg_verifybackup/po/fr.po
+++ b/src/bin/pg_verifybackup/po/fr.po
@@ -498,8 +498,8 @@ msgstr "  -s, --skip-checksums        ignore la vérification des sommes de cont
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/it.po b/src/bin/pg_verifybackup/po/it.po
index 317b0b71e7f..4da68d0074e 100644
--- a/src/bin/pg_verifybackup/po/it.po
+++ b/src/bin/pg_verifybackup/po/it.po
@@ -472,8 +472,8 @@ msgstr "  -s, --skip-checksums         salta la verifica del checksum\n"
 
 #: pg_verifybackup.c:911
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH     usa il percorso specificato per i file WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH     usa il percorso specificato per i file WAL\n"
 
 #: pg_verifybackup.c:912
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ja.po b/src/bin/pg_verifybackup/po/ja.po
index c910fb236cc..a948959b54f 100644
--- a/src/bin/pg_verifybackup/po/ja.po
+++ b/src/bin/pg_verifybackup/po/ja.po
@@ -672,8 +672,8 @@ msgstr "  -s, --skip-checksums        チェックサム検証をスキップ\n"
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    WALファイルに指定したパスを使用する\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    WALファイルに指定したパスを使用する\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ka.po b/src/bin/pg_verifybackup/po/ka.po
index 982751984c7..ef2799316a8 100644
--- a/src/bin/pg_verifybackup/po/ka.po
+++ b/src/bin/pg_verifybackup/po/ka.po
@@ -784,8 +784,8 @@ msgstr "  -s, --skip-checksums        საკონტროლო ჯამ
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ko.po b/src/bin/pg_verifybackup/po/ko.po
index acdc3da5e02..eaf91ef1e98 100644
--- a/src/bin/pg_verifybackup/po/ko.po
+++ b/src/bin/pg_verifybackup/po/ko.po
@@ -501,8 +501,8 @@ msgstr "  -s, --skip-checksums        체크섬 검사 건너뜀\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=경로    WAL 파일이 있는 경로 지정\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=경로    WAL 파일이 있는 경로 지정\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ru.po b/src/bin/pg_verifybackup/po/ru.po
index 64005feedfd..7fb0e5ab1f6 100644
--- a/src/bin/pg_verifybackup/po/ru.po
+++ b/src/bin/pg_verifybackup/po/ru.po
@@ -507,9 +507,9 @@ msgstr "  -s, --skip-checksums        пропустить проверку ко
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
 msgstr ""
-"  -w, --wal-directory=ПУТЬ    использовать заданный путь к файлам WAL\n"
+"  -w, --wal-path=ПУТЬ    использовать заданный путь к файлам WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/sv.po b/src/bin/pg_verifybackup/po/sv.po
index 17240feeb5c..97125838e8c 100644
--- a/src/bin/pg_verifybackup/po/sv.po
+++ b/src/bin/pg_verifybackup/po/sv.po
@@ -492,8 +492,8 @@ msgstr "  -s, --skip-checksums        hoppa över verifiering av kontrollsummor\
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=SÖKVÄG  använd denna sökväg till WAL-filer\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=SÖKVÄG  använd denna sökväg till WAL-filer\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/uk.po b/src/bin/pg_verifybackup/po/uk.po
index 034b9764232..63f8041ab38 100644
--- a/src/bin/pg_verifybackup/po/uk.po
+++ b/src/bin/pg_verifybackup/po/uk.po
@@ -484,8 +484,8 @@ msgstr "  -s, --skip-checksums не перевіряти контрольні с
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH використовувати вказаний шлях для файлів WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH використовувати вказаний шлях для файлів WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_CN.po b/src/bin/pg_verifybackup/po/zh_CN.po
index b7d97c8976d..fb6fcae8b82 100644
--- a/src/bin/pg_verifybackup/po/zh_CN.po
+++ b/src/bin/pg_verifybackup/po/zh_CN.po
@@ -465,8 +465,8 @@ msgstr "  -s, --skip-checksums        跳过校验和验证\n"
 
 #: pg_verifybackup.c:919
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    对WAL文件使用指定路径\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    对WAL文件使用指定路径\n"
 
 #: pg_verifybackup.c:920
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_TW.po b/src/bin/pg_verifybackup/po/zh_TW.po
index c1b710b0a36..568f972b0bb 100644
--- a/src/bin/pg_verifybackup/po/zh_TW.po
+++ b/src/bin/pg_verifybackup/po/zh_TW.po
@@ -555,8 +555,8 @@ msgstr "  -s, --skip-checksums        跳過檢查碼驗證\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    用指定的路徑存放 WAL 檔\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    用指定的路徑存放 WAL 檔\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/t/007_wal.pl b/src/bin/pg_verifybackup/t/007_wal.pl
index babc4f0a86b..b07f80719b0 100644
--- a/src/bin/pg_verifybackup/t/007_wal.pl
+++ b/src/bin/pg_verifybackup/t/007_wal.pl
@@ -42,10 +42,10 @@ command_ok([ 'pg_verifybackup', '--no-parse-wal', $backup_path ],
 command_ok(
 	[
 		'pg_verifybackup',
-		'--wal-directory' => $relocated_pg_wal,
+		'--wal-path' => $relocated_pg_wal,
 		$backup_path
 	],
-	'--wal-directory can be used to specify WAL directory');
+	'--wal-path can be used to specify WAL directory');
 
 # Move directory back to original location.
 rename($relocated_pg_wal, $original_pg_wal) || die "rename pg_wal back: $!";
-- 
2.47.1

From 280432691a9c98b1006d85769ee8e5a5869e55c8 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 24 Jun 2025 11:33:20 +0530
Subject: [PATCH v7 1/8] Refactor: pg_waldump: Move some declarations to new
 pg_waldump.h

This change prepares for a second source file in this directory to
support reading WAL from tar files. Common structures, declarations,
and functions are being exported through this include file so
they can be used in both files.
---
 src/bin/pg_waldump/pg_waldump.c | 11 ++---------
 src/bin/pg_waldump/pg_waldump.h | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 9 deletions(-)
 create mode 100644 src/bin/pg_waldump/pg_waldump.h

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index c6d6ba79e44..5846ee24f46 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -29,6 +29,7 @@
 #include "common/logging.h"
 #include "common/relpath.h"
 #include "getopt_long.h"
+#include "pg_waldump.h"
 #include "rmgrdesc.h"
 #include "storage/bufpage.h"
 
@@ -39,19 +40,11 @@
 
 static const char *progname;
 
-static int	WalSegSz;
+int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 static volatile sig_atomic_t time_to_stop = false;
 
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
-typedef struct XLogDumpPrivate
-{
-	TimeLineID	timeline;
-	XLogRecPtr	startptr;
-	XLogRecPtr	endptr;
-	bool		endptr_reached;
-} XLogDumpPrivate;
-
 typedef struct XLogDumpConfig
 {
 	/* display options */
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
new file mode 100644
index 00000000000..9e62b64ead5
--- /dev/null
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -0,0 +1,27 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_waldump.h - decode and display WAL
+ *
+ * Copyright (c) 2013-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  src/bin/pg_waldump/pg_waldump.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_WALDUMP_H
+#define PG_WALDUMP_H
+
+#include "access/xlogdefs.h"
+
+extern int	WalSegSz;
+
+/* Contains the necessary information to drive WAL decoding */
+typedef struct XLogDumpPrivate
+{
+	TimeLineID	timeline;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
+	bool		endptr_reached;
+} XLogDumpPrivate;
+
+#endif		/* end of PG_WALDUMP_H */
-- 
2.47.1

From 11840029bc52e927858da7be1f91ece9b680d486 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 26 Jun 2025 11:42:53 +0530
Subject: [PATCH v7 2/8] Refactor: pg_waldump: Separate logic used to calculate
 the required read size.

This refactoring prepares the codebase for an upcoming patch that will
support reading WAL from tar files. The logic for calculating the
required read size has been updated to handle both normal WAL files
and WAL files located inside a tar archive.
---
 src/bin/pg_waldump/pg_waldump.c | 39 ++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 5846ee24f46..0dc28ea360c 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -326,6 +326,29 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/* Returns the size in bytes of the data to be read. */
+static inline int
+required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
+				  int reqLen)
+{
+	int			count = XLOG_BLCKSZ;
+
+	if (XLogRecPtrIsValid(private->endptr))
+	{
+		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
+			count = XLOG_BLCKSZ;
+		else if (targetPagePtr + reqLen <= private->endptr)
+			count = private->endptr - targetPagePtr;
+		else
+		{
+			private->endptr_reached = true;
+			return -1;
+		}
+	}
+
+	return count;
+}
+
 /* pg_waldump's XLogReaderRoutine->segment_open callback */
 static void
 WALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
@@ -383,21 +406,11 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = XLOG_BLCKSZ;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
-	if (XLogRecPtrIsValid(private->endptr))
-	{
-		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
-			count = XLOG_BLCKSZ;
-		else if (targetPagePtr + reqLen <= private->endptr)
-			count = private->endptr - targetPagePtr;
-		else
-		{
-			private->endptr_reached = true;
-			return -1;
-		}
-	}
+	if (private->endptr_reached)
+		return -1;
 
 	if (!WALRead(state, readBuff, targetPagePtr, count, private->timeline,
 				 &errinfo))
-- 
2.47.1

From 62a143b267d60d3c98b5063c3874c4c22135d1c0 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 30 Jul 2025 12:43:30 +0530
Subject: [PATCH v7 3/8] Refactor: pg_waldump: Restructure TAP tests.

Restructured some tests to run inside a loop, facilitating their
re-execution for decoding WAL from tar archives.
---
 src/bin/pg_waldump/t/001_basic.pl | 123 ++++++++++++++++--------------
 1 file changed, 67 insertions(+), 56 deletions(-)

diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index f26d75e01cf..1b712e8d74d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -198,28 +198,6 @@ command_like(
 	],
 	qr/./,
 	'runs with start and end segment specified');
-command_fails_like(
-	[ 'pg_waldump', '--path' => $node->data_dir ],
-	qr/error: no start WAL location given/,
-	'path option requires start location');
-command_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-		'--end' => $end_lsn,
-	],
-	qr/./,
-	'runs with path option and start and end locations');
-command_fails_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-	],
-	qr/error: error in WAL record at/,
-	'falling off the end of the WAL results in an error');
-
 command_like(
 	[
 		'pg_waldump', '--quiet',
@@ -227,15 +205,6 @@ command_like(
 	],
 	qr/^$/,
 	'no output with --quiet option');
-command_fails_like(
-	[
-		'pg_waldump', '--quiet',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn
-	],
-	qr/error: error in WAL record at/,
-	'errors are shown with --quiet');
-
 
 # Test for: Display a message that we're skipping data if `from`
 # wasn't a pointer to the start of a record.
@@ -272,7 +241,6 @@ sub test_pg_waldump
 
 	my $result = IPC::Run::run [
 		'pg_waldump',
-		'--path' => $node->data_dir,
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
 		@opts
@@ -288,38 +256,81 @@ sub test_pg_waldump
 
 my @lines;
 
-@lines = test_pg_waldump;
-is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
+my @scenario = (
+	{
+		'path' => $node->data_dir
+	});
 
-@lines = test_pg_waldump('--limit' => 6);
-is(@lines, 6, 'limit option observed');
+for my $scenario (@scenario)
+{
+	my $path = $scenario->{'path'};
 
-@lines = test_pg_waldump('--fullpage');
-is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
+	SKIP:
+	{
+		command_fails_like(
+			[ 'pg_waldump', '--path' => $path ],
+			qr/error: no start WAL location given/,
+			'path option requires start location');
+		command_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+				'--end' => $end_lsn,
+			],
+			qr/./,
+			'runs with path option and start and end locations');
+		command_fails_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+			],
+			qr/error: error in WAL record at/,
+			'falling off the end of the WAL results in an error');
 
-@lines = test_pg_waldump('--stats');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		command_fails_like(
+			[
+				'pg_waldump', '--quiet',
+				'--path' => $path,
+				'--start' => $start_lsn
+			],
+			qr/error: error in WAL record at/,
+			'errors are shown with --quiet');
 
-@lines = test_pg_waldump('--stats=record');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		@lines = test_pg_waldump('--path' => $path);
+		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-@lines = test_pg_waldump('--rmgr' => 'Btree');
-is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		is(@lines, 6, 'limit option observed');
 
-@lines = test_pg_waldump('--fork' => 'init');
-is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
-is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
-	0, 'only lines for selected relation');
+		@lines = test_pg_waldump('--path' => $path, '--stats');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
-	'--block' => 1);
-is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
+		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+
+		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
+		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
+			0, 'only lines for selected relation');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
+			'--block' => 1);
+		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+	}
+}
 
 done_testing();
-- 
2.47.1

From 8a2a15082f43f2cb4c30913f89f749b606ffee13 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 5 Nov 2025 15:40:36 +0530
Subject: [PATCH v7 4/8] pg_waldump: Add support for archived WAL decoding.

pg_waldump can now accept the path to a tar archive containing WAL
files and decode them. This feature was added primarily for
pg_verifybackup, which previously disabled WAL parsing for
tar-formatted backups.

Note that this patch requires that the WAL files within the archive be
in sequential order; an error will be reported otherwise. The next
patch is planned to remove this restriction.
---
 doc/src/sgml/ref/pg_waldump.sgml     |   8 +-
 src/bin/pg_waldump/Makefile          |   7 +-
 src/bin/pg_waldump/archive_waldump.c | 584 +++++++++++++++++++++++++++
 src/bin/pg_waldump/meson.build       |   4 +-
 src/bin/pg_waldump/pg_waldump.c      | 215 +++++++---
 src/bin/pg_waldump/pg_waldump.h      |  36 +-
 src/bin/pg_waldump/t/001_basic.pl    |  84 +++-
 src/tools/pgindent/typedefs.list     |   3 +
 8 files changed, 865 insertions(+), 76 deletions(-)
 create mode 100644 src/bin/pg_waldump/archive_waldump.c

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index ce23add5577..d004bb0f67e 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -141,13 +141,17 @@ PostgreSQL documentation
       <term><option>--path=<replaceable>path</replaceable></option></term>
       <listitem>
        <para>
-        Specifies a directory to search for WAL segment files or a
-        directory with a <literal>pg_wal</literal> subdirectory that
+        Specifies a tar archive or a directory to search for WAL segment files
+        or a directory with a <literal>pg_wal</literal> subdirectory that
         contains such files.  The default is to search in the current
         directory, the <literal>pg_wal</literal> subdirectory of the
         current directory, and the <literal>pg_wal</literal> subdirectory
         of <envar>PGDATA</envar>.
        </para>
+       <para>
+        If a tar archive is provided, its WAL segment files must be in
+        sequential order; otherwise, an error will be reported.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index 4c1ee649501..05ac5763a57 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -3,6 +3,9 @@
 PGFILEDESC = "pg_waldump - decode and display WAL"
 PGAPPICON=win32
 
+# make these available to TAP test scripts
+export TAR
+
 subdir = src/bin/pg_waldump
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
@@ -12,11 +15,13 @@ OBJS = \
 	$(WIN32RES) \
 	compat.o \
 	pg_waldump.o \
+	archive_waldump.o \
 	rmgrdesc.o \
 	xlogreader.o \
 	xlogstats.o
 
-override CPPFLAGS := -DFRONTEND $(CPPFLAGS)
+override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
new file mode 100644
index 00000000000..61d6782f9b7
--- /dev/null
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -0,0 +1,584 @@
+/*-------------------------------------------------------------------------
+ *
+ * archive_waldump.c
+ *		A generic facility for reading WAL data from tar archives via archive
+ *		streamer.
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/bin/pg_waldump/archive_waldump.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <unistd.h>
+
+#include "access/xlog_internal.h"
+#include "common/hashfn.h"
+#include "common/logging.h"
+#include "fe_utils/simple_list.h"
+#include "pg_waldump.h"
+
+/*
+ * How many bytes should we try to read from a file at once?
+ */
+#define READ_CHUNK_SIZE				(128 * 1024)
+
+/* Structure for storing the WAL segment data from the archive */
+typedef struct ArchivedWALEntry
+{
+	uint32		status;			/* hash status */
+	XLogSegNo	segno;			/* hash key: WAL segment number */
+	TimeLineID	timeline;		/* timeline of this wal file */
+
+	StringInfoData buf;
+	bool		tmpseg_exists;	/* spill file exists? */
+
+	int			total_read;		/* total read of this WAL segment, including
+								 * buffered and temporarily written data */
+} ArchivedWALEntry;
+
+#define SH_PREFIX				ArchivedWAL
+#define SH_ELEMENT_TYPE			ArchivedWALEntry
+#define SH_KEY_TYPE				XLogSegNo
+#define SH_KEY					segno
+#define SH_HASH_KEY(tb, key)	murmurhash64((uint64) key)
+#define SH_EQUAL(tb, a, b)		(a == b)
+#define SH_GET_HASH(tb, a)		a->hash
+#define SH_SCOPE				static inline
+#define SH_RAW_ALLOCATOR		pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static ArchivedWAL_hash *ArchivedWAL_HTAB = NULL;
+
+typedef struct astreamer_waldump
+{
+	astreamer	base;
+	XLogDumpPrivate *privateInfo;
+} astreamer_waldump;
+
+static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
+static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
+											   XLogDumpPrivate *privateInfo);
+
+static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
+static void astreamer_waldump_content(astreamer *streamer,
+									  astreamer_member *member,
+									  const char *data, int len,
+									  astreamer_archive_context context);
+static void astreamer_waldump_finalize(astreamer *streamer);
+static void astreamer_waldump_free(astreamer *streamer);
+
+static bool member_is_wal_file(astreamer_waldump *mystreamer,
+							   astreamer_member *member,
+							   XLogSegNo *curSegNo,
+							   TimeLineID *curTimeline);
+
+static const astreamer_ops astreamer_waldump_ops = {
+	.content = astreamer_waldump_content,
+	.finalize = astreamer_waldump_finalize,
+	.free = astreamer_waldump_free
+};
+
+/*
+ * Returns true if the given file is a tar archive and outputs its compression
+ * algorithm.
+ */
+bool
+is_archive_file(const char *fname, pg_compress_algorithm *compression)
+{
+	int			fname_len = strlen(fname);
+	pg_compress_algorithm compress_algo;
+
+	/* Now, check the compression type of the tar */
+	if (fname_len > 4 &&
+		strcmp(fname + fname_len - 4, ".tar") == 0)
+		compress_algo = PG_COMPRESSION_NONE;
+	else if (fname_len > 4 &&
+			 strcmp(fname + fname_len - 4, ".tgz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 7 &&
+			 strcmp(fname + fname_len - 7, ".tar.gz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.lz4") == 0)
+		compress_algo = PG_COMPRESSION_LZ4;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.zst") == 0)
+		compress_algo = PG_COMPRESSION_ZSTD;
+	else
+		return false;
+
+	*compression = compress_algo;
+
+	return true;
+}
+
+/*
+ * Initializes the tar archive reader to read WAL files from the archive,
+ * creates a hash table to store them, performs quick existence checks for WAL
+ * entries in the archive and retrieves the WAL segment size, and sets up
+ * filtering criteria for relevant entries.
+ */
+void
+init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
+					pg_compress_algorithm compression)
+{
+	int			fd;
+	astreamer  *streamer;
+	ArchivedWALEntry *entry = NULL;
+	XLogLongPageHeader longhdr;
+
+	/* Open tar archive and store its file descriptor */
+	fd = open_file_in_directory(waldir, privateInfo->archive_name);
+
+	if (fd < 0)
+		pg_fatal("could not open file \"%s\"", privateInfo->archive_name);
+
+	privateInfo->archive_fd = fd;
+
+	streamer = astreamer_waldump_new(privateInfo);
+
+	/* Before that we must parse the tar archive. */
+	streamer = astreamer_tar_parser_new(streamer);
+
+	/* Before that we must decompress, if archive is compressed. */
+	if (compression == PG_COMPRESSION_GZIP)
+		streamer = astreamer_gzip_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_LZ4)
+		streamer = astreamer_lz4_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_ZSTD)
+		streamer = astreamer_zstd_decompressor_new(streamer);
+
+	privateInfo->archive_streamer = streamer;
+
+	/* Hash table storing WAL entries read from the archive */
+	ArchivedWAL_HTAB = ArchivedWAL_create(16, NULL);
+
+	/*
+	 * Verify that the archive contains valid WAL files and fetch WAL segment
+	 * size
+	 */
+	while (entry == NULL || entry->buf.len < XLOG_BLCKSZ)
+	{
+		if (read_archive_file(privateInfo, XLOG_BLCKSZ) == 0)
+			pg_fatal("could not find WAL in \"%s\" archive",
+					 privateInfo->archive_name);
+
+		entry = privateInfo->cur_wal;
+	}
+
+	/* Set WalSegSz if WAL data is successfully read */
+	longhdr = (XLogLongPageHeader) entry->buf.data;
+
+	WalSegSz = longhdr->xlp_seg_size;
+
+	if (!IsValidWalSegSize(WalSegSz))
+	{
+		pg_log_error(ngettext("invalid WAL segment size in WAL file from archive \"%s\" (%d byte)",
+							  "invalid WAL segment size in WAL file from archive \"%s\" (%d bytes)",
+							  WalSegSz),
+					 privateInfo->archive_name, WalSegSz);
+		pg_log_error_detail("The WAL segment size must be a power of two between 1 MB and 1 GB.");
+		exit(1);
+	}
+
+	/*
+	 * With the WAL segment size available, we can now initialize the
+	 * dependent start and end segment numbers.
+	 */
+	XLByteToSeg(privateInfo->startptr, privateInfo->startSegNo, WalSegSz);
+	XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+}
+
+/*
+ * Release the archive streamer chain and close the archive file.
+ */
+void
+free_archive_reader(XLogDumpPrivate *privateInfo)
+{
+	/*
+	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
+	 * flush any remaining buffered data or to ensure the end of the tar
+	 * archive is reached. However, when decoding a WAL file, once we hit the
+	 * end LSN, any remaining WAL data in the buffer or the tar archive's
+	 * unreached end can be safely ignored.
+	 */
+	astreamer_free(privateInfo->archive_streamer);
+
+	/* Close the file. */
+	if (close(privateInfo->archive_fd) != 0)
+		pg_log_error("could not close file \"%s\": %m",
+					 privateInfo->archive_name);
+}
+
+/*
+ * Copies WAL data from astreamer to readBuff; if unavailable, fetches more
+ * from the tar archive via astreamer.
+ */
+int
+read_archive_wal_page(XLogDumpPrivate *privateInfo, XLogRecPtr targetPagePtr,
+					  Size count, char *readBuff)
+{
+	char	   *p = readBuff;
+	Size		nbytes = count;
+	XLogRecPtr	recptr = targetPagePtr;
+	XLogSegNo	segno;
+	ArchivedWALEntry *entry;
+
+	XLByteToSeg(targetPagePtr, segno, WalSegSz);
+	entry = get_archive_wal_entry(segno, privateInfo);
+
+	while (nbytes > 0)
+	{
+		char	   *buf = entry->buf.data;
+		int			len = entry->buf.len;
+
+		/* WAL record range that the buffer contains */
+		XLogRecPtr	endPtr;
+		XLogRecPtr	startPtr;
+
+		XLogSegNoOffsetToRecPtr(entry->segno, entry->total_read,
+								WalSegSz, endPtr);
+		startPtr = endPtr - len;
+
+		/*
+		 * pg_waldump may request to re-read the currently active page, but
+		 * never a page older than the current one. Therefore, any fully
+		 * consumed WAL data preceding the current page can be safely
+		 * discarded.
+		 */
+		if (recptr >= endPtr)
+		{
+			/* Discard the buffered data */
+			resetStringInfo(&entry->buf);
+			len = 0;
+
+			/*
+			 * Push back the partial page data for the current page to the
+			 * buffer, ensuring it remains available for re-reading if
+			 * requested.
+			 */
+			if (p > readBuff)
+			{
+				Assert((count - nbytes) > 0);
+				appendBinaryStringInfo(&entry->buf, readBuff, count - nbytes);
+			}
+		}
+
+		if (len > 0 && recptr > startPtr)
+		{
+			int			skipBytes = 0;
+
+			/*
+			 * The required offset is not at the start of the buffer, so skip
+			 * bytes until reaching the desired offset of the target page.
+			 */
+			skipBytes = recptr - startPtr;
+
+			buf += skipBytes;
+			len -= skipBytes;
+		}
+
+		if (len > 0)
+		{
+			int			readBytes = len >= nbytes ? nbytes : len;
+
+			/* Ensure the reading page is in the buffer */
+			Assert(recptr >= startPtr && recptr < endPtr);
+
+			memcpy(p, buf, readBytes);
+
+			/* Update state for read */
+			nbytes -= readBytes;
+			p += readBytes;
+			recptr += readBytes;
+		}
+		else
+		{
+			/*
+			 * Fetch more data; raise an error if it's not the current segment
+			 * being read by the archive streamer or if reading of the
+			 * archived file has finished.
+			 */
+			if (privateInfo->cur_wal != entry ||
+				read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+			{
+				char		fname[MAXFNAMELEN];
+
+				XLogFileName(fname, privateInfo->timeline, entry->segno,
+							 WalSegSz);
+				pg_fatal("could not read file \"%s\" from archive \"%s\": read %lld of %lld",
+						 fname, privateInfo->archive_name,
+						 (long long int) count - nbytes,
+						 (long long int) nbytes);
+			}
+		}
+	}
+
+	/*
+	 * Should have either have successfully read all the requested bytes or
+	 * reported a failure before this point.
+	 */
+	Assert(nbytes == 0);
+
+	/*
+	 * NB: We return the fixed value provided as input. Although we could
+	 * return a boolean since we either successfully read the WAL page or
+	 * raise an error, but the caller expects this value to be returned. The
+	 * routine that reads WAL pages from the physical WAL file follows the
+	 * same convention.
+	 */
+	return count;
+}
+
+/*
+ * Reads the archive file and passes it to the archive streamer for
+ * decompression.
+ */
+static int
+read_archive_file(XLogDumpPrivate *privateInfo, Size count)
+{
+	int			rc;
+	char	   *buffer;
+
+	buffer = pg_malloc(READ_CHUNK_SIZE * sizeof(uint8));
+
+	rc = read(privateInfo->archive_fd, buffer, count);
+	if (rc < 0)
+		pg_fatal("could not read file \"%s\": %m",
+				 privateInfo->archive_name);
+
+	/*
+	 * Decompress (if required), and then parse the previously read contents
+	 * of the tar file.
+	 */
+	if (rc > 0)
+		astreamer_content(privateInfo->archive_streamer, NULL,
+						  buffer, rc, ASTREAMER_UNKNOWN);
+	pg_free(buffer);
+
+	return rc;
+}
+
+/*
+ * Returns the archived WAL entry from the hash table if it exists. Otherwise,
+ * it invokes the routine to read the archived file and retrieve the entry if
+ * it is not already in hash table.
+ */
+static ArchivedWALEntry *
+get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
+{
+	ArchivedWALEntry *entry = NULL;
+	char		fname[MAXFNAMELEN];
+
+	/* Search hash table */
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry != NULL)
+		return entry;
+
+	/* Needed WAL yet to be decoded from archive, do the same */
+	while (1)
+	{
+		entry = privateInfo->cur_wal;
+
+		/* Fetch more data */
+		if (entry == NULL || entry->buf.len == 0)
+		{
+			if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+				break;			/* archive file ended */
+		}
+
+		/*
+		 * Either, here for the first time, or the archived streamer is
+		 * reading a non-WAL file or an irrelevant WAL file.
+		 */
+		if (entry == NULL)
+			continue;
+
+		/* Found the required entry */
+		if (entry->segno == segno)
+			return entry;
+
+		/*
+		 * Ignore if the timeline is different or the current segment is not
+		 * the desired one.
+		 */
+		if (privateInfo->timeline != entry->timeline ||
+			privateInfo->startSegNo > entry->segno ||
+			privateInfo->endSegNo < entry->segno)
+		{
+			privateInfo->cur_wal = NULL;
+			continue;
+		}
+
+		/* WAL segments must be archived in order */
+		pg_log_error("WAL files are not archived in sequential order");
+		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
+							segno, entry->segno);
+		exit(1);
+	}
+
+	/* Requested WAL segment not found */
+	XLogFileName(fname, privateInfo->timeline, segno, WalSegSz);
+	pg_fatal("could not find file \"%s\" in archive", fname);
+}
+
+/*
+ * Create an astreamer that can read WAL from tar file.
+ */
+static astreamer *
+astreamer_waldump_new(XLogDumpPrivate *privateInfo)
+{
+	astreamer_waldump *streamer;
+
+	streamer = palloc0(sizeof(astreamer_waldump));
+	*((const astreamer_ops **) &streamer->base.bbs_ops) =
+		&astreamer_waldump_ops;
+
+	streamer->privateInfo = privateInfo;
+
+	return &streamer->base;
+}
+
+/*
+ * Main entry point of the archive streamer for reading WAL data from a tar
+ * file. If a member is identified as a valid WAL file, a hash entry is created
+ * for it, and its contents are copied into that entry's buffer, making them
+ * accessible to the decoding routine.
+ */
+static void
+astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
+						  const char *data, int len,
+						  astreamer_archive_context context)
+{
+	astreamer_waldump *mystreamer = (astreamer_waldump *) streamer;
+	XLogDumpPrivate *privateInfo = mystreamer->privateInfo;
+
+	Assert(context != ASTREAMER_UNKNOWN);
+
+	switch (context)
+	{
+		case ASTREAMER_MEMBER_HEADER:
+			{
+				XLogSegNo	segno;
+				TimeLineID	timeline;
+				ArchivedWALEntry *entry;
+				bool		found;
+
+				pg_log_debug("reading \"%s\"", member->pathname);
+
+				if (!member_is_wal_file(mystreamer, member,
+										&segno, &timeline))
+					break;
+
+				entry = ArchivedWAL_insert(ArchivedWAL_HTAB, segno, &found);
+
+				/*
+				 * Shouldn't happen, but if it does, simply ignore the
+				 * duplicate WAL file.
+				 */
+				if (found)
+				{
+					pg_log_warning("ignoring duplicate WAL file found in archive: \"%s\"",
+								   member->pathname);
+					break;
+				}
+
+				initStringInfo(&entry->buf);
+				entry->timeline = timeline;
+				entry->total_read = 0;
+
+				privateInfo->cur_wal = entry;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_CONTENTS:
+			if (privateInfo->cur_wal)
+			{
+				appendBinaryStringInfo(&privateInfo->cur_wal->buf, data, len);
+				privateInfo->cur_wal->total_read += len;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_TRAILER:
+			privateInfo->cur_wal = NULL;
+			break;
+
+		case ASTREAMER_ARCHIVE_TRAILER:
+			break;
+
+		default:
+			/* Shouldn't happen. */
+			pg_fatal("unexpected state while parsing tar file");
+	}
+}
+
+/*
+ * End-of-stream processing for a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_finalize(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+}
+
+/*
+ * Free memory associated with a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_free(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+	pfree(streamer);
+}
+
+/*
+ * Returns true if the archive member name matches the WAL naming format. If
+ * successful, it also outputs the WAL segment number, and timeline.
+ */
+static bool
+member_is_wal_file(astreamer_waldump *mystreamer, astreamer_member *member,
+				   XLogSegNo *curSegNo, TimeLineID *curTimeline)
+{
+	int			pathlen;
+	XLogSegNo	segNo;
+	TimeLineID	timeline;
+	char	   *fname;
+
+	/* We are only interested in normal files. */
+	if (member->is_directory || member->is_link)
+		return false;
+
+	pathlen = strlen(member->pathname);
+	if (pathlen < XLOG_FNAME_LEN)
+		return false;
+
+	/* WAL file could be with full path */
+	fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+	if (!IsXLogFileName(fname))
+		return false;
+
+	/*
+	 * XXX: On some systems (e.g., OpenBSD), the tar utility includes
+	 * PaxHeaders when creating an archive. These are special entries that
+	 * store extended metadata for the file entry immediately following them,
+	 * and they share the exact same name as that file.
+	 */
+	if (strstr(member->pathname, "PaxHeaders."))
+		return false;
+
+	/* Parse position from file */
+	XLogFromFileName(fname, &timeline, &segNo, WalSegSz);
+
+	*curSegNo = segNo;
+	*curTimeline = timeline;
+
+	return true;
+}
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 937e0d68841..da00746587c 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -3,6 +3,7 @@
 pg_waldump_sources = files(
   'compat.c',
   'pg_waldump.c',
+  'archive_waldump.c',
   'rmgrdesc.c',
 )
 
@@ -18,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, lz4, zstd],
+  dependencies: [frontend_code, lz4, zstd, libpq],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
@@ -29,6 +30,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'TAR': tar.found() ? tar.full_path() : ''},
     'tests': [
       't/001_basic.pl',
       't/002_save_fullpage.pl',
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 0dc28ea360c..02ad141e44a 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -177,7 +177,7 @@ split_path(const char *path, char **dir, char **fname)
  *
  * return a read only fd
  */
-static int
+int
 open_file_in_directory(const char *directory, const char *fname)
 {
 	int			fd = -1;
@@ -436,6 +436,44 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 	return count;
 }
 
+/*
+ * pg_waldump's XLogReaderRoutine->segment_open callback to support dumping WAL
+ * files from tar archives.
+ */
+static void
+TarWALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
+					  TimeLineID *tli_p)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->segment_close callback.
+ */
+static void
+TarWALDumpCloseSegment(XLogReaderState *state)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->page_read callback to support dumping WAL
+ * files from tar archives.
+ */
+static int
+TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				   XLogRecPtr targetPtr, char *readBuff)
+{
+	XLogDumpPrivate *private = state->private_data;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
+
+	if (private->endptr_reached)
+		return -1;
+
+	/* Read the WAL page from the archive streamer */
+	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
+}
+
 /*
  * Boolean to return whether the given WAL record matches a specific relation
  * and optionally block.
@@ -773,8 +811,8 @@ usage(void)
 	printf(_("  -F, --fork=FORK        only show records that modify blocks in fork FORK;\n"
 			 "                         valid names are main, fsm, vm, init\n"));
 	printf(_("  -n, --limit=N          number of records to display\n"));
-	printf(_("  -p, --path=PATH        directory in which to find WAL segment files or a\n"
-			 "                         directory with a ./pg_wal that contains such files\n"
+	printf(_("  -p, --path=PATH        tar archive or a directory in which to find WAL segment files or\n"
+			 "                         a directory with a ./pg_wal that contains such files\n"
 			 "                         (default: current directory, ./pg_wal, $PGDATA/pg_wal)\n"));
 	printf(_("  -q, --quiet            do not print any output, except for errors\n"));
 	printf(_("  -r, --rmgr=RMGR        only show records generated by resource manager RMGR;\n"
@@ -806,7 +844,10 @@ main(int argc, char **argv)
 	XLogRecord *record;
 	XLogRecPtr	first_record;
 	char	   *waldir = NULL;
+	char	   *walpath = NULL;
 	char	   *errormsg;
+	bool		is_archive = false;
+	pg_compress_algorithm compression;
 
 	static struct option long_options[] = {
 		{"bkp-details", no_argument, NULL, 'b'},
@@ -938,7 +979,7 @@ main(int argc, char **argv)
 				}
 				break;
 			case 'p':
-				waldir = pg_strdup(optarg);
+				walpath = pg_strdup(optarg);
 				break;
 			case 'q':
 				config.quiet = true;
@@ -1102,10 +1143,20 @@ main(int argc, char **argv)
 		goto bad_argument;
 	}
 
-	if (waldir != NULL)
+	if (walpath != NULL)
 	{
+		/* validate path points to tar archive */
+		if (is_archive_file(walpath, &compression))
+		{
+			char	   *fname = NULL;
+
+			split_path(walpath, &waldir, &fname);
+
+			private.archive_name = fname;
+			is_archive = true;
+		}
 		/* validate path points to directory */
-		if (!verify_directory(waldir))
+		else if (!verify_directory(walpath))
 		{
 			pg_log_error("could not open directory \"%s\": %m", waldir);
 			goto bad_argument;
@@ -1123,6 +1174,17 @@ main(int argc, char **argv)
 		int			fd;
 		XLogSegNo	segno;
 
+		/*
+		 * If a tar archive is passed using the --path option, all other
+		 * arguments become unnecessary.
+		 */
+		if (is_archive)
+		{
+			pg_log_error("unnecessary command-line arguments specified with tar archive (first is \"%s\")",
+						 argv[optind]);
+			goto bad_argument;
+		}
+
 		split_path(argv[optind], &directory, &fname);
 
 		if (waldir == NULL && directory != NULL)
@@ -1133,69 +1195,77 @@ main(int argc, char **argv)
 				pg_fatal("could not open directory \"%s\": %m", waldir);
 		}
 
-		waldir = identify_target_directory(waldir, fname);
-		fd = open_file_in_directory(waldir, fname);
-		if (fd < 0)
-			pg_fatal("could not open file \"%s\"", fname);
-		close(fd);
-
-		/* parse position from file */
-		XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
-
-		if (!XLogRecPtrIsValid(private.startptr))
-			XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
-		else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+		if (fname != NULL && is_archive_file(fname, &compression))
 		{
-			pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.startptr),
-						 fname);
-			goto bad_argument;
+			private.archive_name = fname;
+			is_archive = true;
 		}
-
-		/* no second file specified, set end position */
-		if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
-			XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
-
-		/* parse ENDSEG if passed */
-		if (optind + 1 < argc)
+		else
 		{
-			XLogSegNo	endsegno;
-
-			/* ignore directory, already have that */
-			split_path(argv[optind + 1], &directory, &fname);
-
+			waldir = identify_target_directory(waldir, fname);
 			fd = open_file_in_directory(waldir, fname);
 			if (fd < 0)
 				pg_fatal("could not open file \"%s\"", fname);
 			close(fd);
 
 			/* parse position from file */
-			XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+			XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
 
-			if (endsegno < segno)
-				pg_fatal("ENDSEG %s is before STARTSEG %s",
-						 argv[optind + 1], argv[optind]);
+			if (!XLogRecPtrIsValid(private.startptr))
+				XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
+			else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+			{
+				pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.startptr),
+							 fname);
+				goto bad_argument;
+			}
 
-			if (!XLogRecPtrIsValid(private.endptr))
-				XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
-										private.endptr);
+			/* no second file specified, set end position */
+			if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
+				XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
 
-			/* set segno to endsegno for check of --end */
-			segno = endsegno;
-		}
+			/* parse ENDSEG if passed */
+			if (optind + 1 < argc)
+			{
+				XLogSegNo	endsegno;
 
+				/* ignore directory, already have that */
+				split_path(argv[optind + 1], &directory, &fname);
 
-		if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
-			private.endptr != (segno + 1) * WalSegSz)
-		{
-			pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.endptr),
-						 argv[argc - 1]);
-			goto bad_argument;
+				fd = open_file_in_directory(waldir, fname);
+				if (fd < 0)
+					pg_fatal("could not open file \"%s\"", fname);
+				close(fd);
+
+				/* parse position from file */
+				XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+
+				if (endsegno < segno)
+					pg_fatal("ENDSEG %s is before STARTSEG %s",
+							 argv[optind + 1], argv[optind]);
+
+				if (!XLogRecPtrIsValid(private.endptr))
+					XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
+											private.endptr);
+
+				/* set segno to endsegno for check of --end */
+				segno = endsegno;
+			}
+
+
+			if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
+				private.endptr != (segno + 1) * WalSegSz)
+			{
+				pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.endptr),
+							 argv[argc - 1]);
+				goto bad_argument;
+			}
 		}
 	}
-	else
-		waldir = identify_target_directory(waldir, NULL);
+	else if (!is_archive)
+		waldir = identify_target_directory(walpath, NULL);
 
 	/* we don't know what to print */
 	if (!XLogRecPtrIsValid(private.startptr))
@@ -1207,12 +1277,36 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
-	xlogreader_state =
-		XLogReaderAllocate(WalSegSz, waldir,
-						   XL_ROUTINE(.page_read = WALDumpReadPage,
-									  .segment_open = WALDumpOpenSegment,
-									  .segment_close = WALDumpCloseSegment),
-						   &private);
+	if (is_archive)
+	{
+		/*
+		 * A NULL WAL directory indicates that the archive file is located
+		 * in the current working directory of the pg_waldump execution
+		 */
+		waldir = waldir ? pg_strdup(waldir) : pg_strdup(".");
+
+		/* Set up for reading tar file */
+		init_archive_reader(&private, waldir, compression);
+
+		/* Routine to decode WAL files in tar archive */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = TarWALDumpReadPage,
+										  .segment_open = TarWALDumpOpenSegment,
+										  .segment_close = TarWALDumpCloseSegment),
+							   &private);
+	}
+	else
+	{
+		/* Routine to decode WAL files */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = WALDumpReadPage,
+										  .segment_open = WALDumpOpenSegment,
+										  .segment_close = WALDumpCloseSegment),
+							   &private);
+	}
+
 	if (!xlogreader_state)
 		pg_fatal("out of memory while allocating a WAL reading processor");
 
@@ -1321,6 +1415,9 @@ main(int argc, char **argv)
 
 	XLogReaderFree(xlogreader_state);
 
+	if (is_archive)
+		free_archive_reader(&private);
+
 	return EXIT_SUCCESS;
 
 bad_argument:
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 9e62b64ead5..54758c3548a 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -12,9 +12,13 @@
 #define PG_WALDUMP_H
 
 #include "access/xlogdefs.h"
+#include "fe_utils/astreamer.h"
 
 extern int	WalSegSz;
 
+/* Forward declaration */
+struct ArchivedWALEntry;
+
 /* Contains the necessary information to drive WAL decoding */
 typedef struct XLogDumpPrivate
 {
@@ -22,6 +26,36 @@ typedef struct XLogDumpPrivate
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	bool		endptr_reached;
+
+	/* Fields required to read WAL from archive */
+	char	   *archive_name;	/* Tar archive name */
+	int			archive_fd;		/* File descriptor for the open tar file */
+
+	astreamer  *archive_streamer;
+
+	/* What the archive streamer is currently reading */
+	struct ArchivedWALEntry *cur_wal;
+
+	/*
+	 * Although these values can be easily derived from startptr and endptr,
+	 * doing so repeatedly for each archived member would be inefficient, as
+	 * it would involve recalculating and filtering out irrelevant WAL
+	 * segments.
+	 */
+	XLogSegNo	startSegNo;
+	XLogSegNo	endSegNo;
 } XLogDumpPrivate;
 
-#endif		/* end of PG_WALDUMP_H */
+extern int	open_file_in_directory(const char *directory, const char *fname);
+
+extern bool is_archive_file(const char *fname,
+							pg_compress_algorithm *compression);
+extern void init_archive_reader(XLogDumpPrivate *privateInfo,
+								const char *waldir,
+								pg_compress_algorithm compression);
+extern void free_archive_reader(XLogDumpPrivate *privateInfo);
+extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
+								  XLogRecPtr targetPagePtr,
+								  Size count, char *readBuff);
+
+#endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 1b712e8d74d..443126a9ce6 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -3,10 +3,13 @@
 
 use strict;
 use warnings FATAL => 'all';
+use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
 
+my $tar = $ENV{TAR};
+
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
 program_options_handling_ok('pg_waldump');
@@ -235,7 +238,7 @@ command_like(
 sub test_pg_waldump
 {
 	local $Test::Builder::Level = $Test::Builder::Level + 1;
-	my @opts = @_;
+	my ($path, @opts) = @_;
 
 	my ($stdout, $stderr);
 
@@ -243,6 +246,7 @@ sub test_pg_waldump
 		'pg_waldump',
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
+		'--path' => $path,
 		@opts
 	  ],
 	  '>' => \$stdout,
@@ -254,11 +258,50 @@ sub test_pg_waldump
 	return @lines;
 }
 
-my @lines;
+# Create a tar archive, sorting the file order
+sub generate_archive
+{
+	my ($archive, $directory, $compression_flags) = @_;
+
+	my @files;
+	opendir my $dh, $directory or die "opendir: $!";
+	while (my $entry = readdir $dh) {
+		# Skip '.' and '..'
+		next if $entry eq '.' || $entry eq '..';
+		push @files, $entry;
+	}
+	closedir $dh;
+
+	@files = sort @files;
+
+	# move into the WAL directory before archiving files
+	my $cwd = getcwd;
+	chdir($directory) || die "chdir: $!";
+	command_ok([$tar, $compression_flags, $archive, @files]);
+	chdir($cwd) || die "chdir: $!";
+}
+
+my $tmp_dir = PostgreSQL::Test::Utils::tempdir_short();
 
 my @scenario = (
 	{
-		'path' => $node->data_dir
+		'path' => $node->data_dir,
+		'is_archive' => 0,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar",
+		'compression_method' => 'none',
+		'compression_flags' => '-cf',
+		'is_archive' => 1,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar.gz",
+		'compression_method' => 'gzip',
+		'compression_flags' => '-czf',
+		'is_archive' => 1,
+		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
 	});
 
 for my $scenario (@scenario)
@@ -267,6 +310,19 @@ for my $scenario (@scenario)
 
 	SKIP:
 	{
+		skip "tar command is not available", 3
+		  if !defined $tar;
+		skip "$scenario->{'compression_method'} compression not supported by this build", 3
+		  if !$scenario->{'enabled'} && $scenario->{'is_archive'};
+
+		  # create pg_wal archive
+		  if ($scenario->{'is_archive'})
+		  {
+			  generate_archive($path,
+				  $node->data_dir . '/pg_wal',
+				  $scenario->{'compression_flags'});
+		  }
+
 		command_fails_like(
 			[ 'pg_waldump', '--path' => $path ],
 			qr/error: no start WAL location given/,
@@ -298,38 +354,42 @@ for my $scenario (@scenario)
 			qr/error: error in WAL record at/,
 			'errors are shown with --quiet');
 
-		@lines = test_pg_waldump('--path' => $path);
+		my @lines;
+		@lines = test_pg_waldump($path);
 		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		@lines = test_pg_waldump($path, '--limit' => 6);
 		is(@lines, 6, 'limit option observed');
 
-		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		@lines = test_pg_waldump($path, '--fullpage');
 		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats');
+		@lines = test_pg_waldump($path, '--stats');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		@lines = test_pg_waldump($path, '--stats=record');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		@lines = test_pg_waldump($path, '--rmgr' => 'Btree');
 		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		@lines = test_pg_waldump($path, '--fork' => 'init');
 		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
 		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
 			0, 'only lines for selected relation');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
 			'--block' => 1);
 		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+
+		# Cleanup.
+		unlink $path if $scenario->{'is_archive'};
 	}
 }
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index c751c25a04d..c38a1c3808b 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -139,6 +139,8 @@ ArchiveOpts
 ArchiveShutdownCB
 ArchiveStartupCB
 ArchiveStreamState
+ArchivedWALEntry
+ArchivedWAL_hash
 ArchiverOutput
 ArchiverStage
 ArrayAnalyzeExtraData
@@ -3465,6 +3467,7 @@ astreamer_recovery_injector
 astreamer_tar_archiver
 astreamer_tar_parser
 astreamer_verify
+astreamer_waldump
 astreamer_zstd_frame
 auth_password_hook_typ
 autovac_table
-- 
2.47.1

From b0eae9adecb56bf634a9193910b702712f6b72dc Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 17 Jul 2025 16:39:36 +0530
Subject: [PATCH v7 8/8] pg_verifybackup: enabled WAL parsing for tar-format
 backup

Now that pg_waldump supports decoding from tar archives, we should
leverage this functionality to remove the previous restriction on WAL
parsing for tar-backed formats.
---
 doc/src/sgml/ref/pg_verifybackup.sgml         |  5 +-
 src/bin/pg_verifybackup/pg_verifybackup.c     | 66 +++++++++++++------
 src/bin/pg_verifybackup/t/002_algorithm.pl    |  4 --
 src/bin/pg_verifybackup/t/003_corruption.pl   |  4 +-
 src/bin/pg_verifybackup/t/008_untar.pl        |  5 +-
 src/bin/pg_verifybackup/t/010_client_untar.pl |  5 +-
 6 files changed, 50 insertions(+), 39 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index e9b8bfd51b1..16b50b5a4df 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -36,10 +36,7 @@ PostgreSQL documentation
    <literal>backup_manifest</literal> generated by the server at the time
    of the backup. The backup may be stored either in the "plain" or the "tar"
    format; this includes tar-format backups compressed with any algorithm
-   supported by <application>pg_basebackup</application>. However, at present,
-   <literal>WAL</literal> verification is supported only for plain-format
-   backups. Therefore, if the backup is stored in tar-format, the
-   <literal>-n, --no-parse-wal</literal> option should be used.
+   supported by <application>pg_basebackup</application>.
   </para>
 
   <para>
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 9fcd6be004e..6915fc7f28e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -74,7 +74,9 @@ pg_noreturn static void report_manifest_error(JsonManifestParseContext *context,
 											  const char *fmt,...)
 			pg_attribute_printf(2, 3);
 
-static void verify_tar_backup(verifier_context *context, DIR *dir);
+static void verify_tar_backup(verifier_context *context, DIR *dir,
+							  char **base_archive_path,
+							  char **wal_archive_path);
 static void verify_plain_backup_directory(verifier_context *context,
 										  char *relpath, char *fullpath,
 										  DIR *dir);
@@ -83,7 +85,9 @@ static void verify_plain_backup_file(verifier_context *context, char *relpath,
 static void verify_control_file(const char *controlpath,
 								uint64 manifest_system_identifier);
 static void precheck_tar_backup_file(verifier_context *context, char *relpath,
-									 char *fullpath, SimplePtrList *tarfiles);
+									 char *fullpath, SimplePtrList *tarfiles,
+									 char **base_archive_path,
+									 char **wal_archive_path);
 static void verify_tar_file(verifier_context *context, char *relpath,
 							char *fullpath, astreamer *streamer);
 static void report_extra_backup_files(verifier_context *context);
@@ -136,6 +140,8 @@ main(int argc, char **argv)
 	bool		no_parse_wal = false;
 	bool		quiet = false;
 	char	   *wal_path = NULL;
+	char	   *base_archive_path = NULL;
+	char	   *wal_archive_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -327,17 +333,6 @@ main(int argc, char **argv)
 		pfree(path);
 	}
 
-	/*
-	 * XXX: In the future, we should consider enhancing pg_waldump to read WAL
-	 * files from an archive.
-	 */
-	if (!no_parse_wal && context.format == 't')
-	{
-		pg_log_error("pg_waldump cannot read tar files");
-		pg_log_error_hint("You must use -n/--no-parse-wal when verifying a tar-format backup.");
-		exit(1);
-	}
-
 	/*
 	 * Perform the appropriate type of verification appropriate based on the
 	 * backup format. This will close 'dir'.
@@ -346,7 +341,7 @@ main(int argc, char **argv)
 		verify_plain_backup_directory(&context, NULL, context.backup_directory,
 									  dir);
 	else
-		verify_tar_backup(&context, dir);
+		verify_tar_backup(&context, dir, &base_archive_path, &wal_archive_path);
 
 	/*
 	 * The "matched" flag should now be set on every entry in the hash table.
@@ -364,9 +359,28 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
-	/* By default, look for the WAL in the backup directory, too. */
+	/*
+	 * By default, WAL files are expected to be found in the backup directory
+	 * for plain-format backups. In the case of tar-format backups, if a
+	 * separate WAL archive is not found, the WAL files are most likely
+	 * included within the main data directory archive.
+	 */
 	if (wal_path == NULL)
-		wal_path = psprintf("%s/pg_wal", context.backup_directory);
+	{
+		if (context.format == 'p')
+			wal_path = psprintf("%s/pg_wal", context.backup_directory);
+		else if (wal_archive_path)
+			wal_path = wal_archive_path;
+		else if (base_archive_path)
+			wal_path = base_archive_path;
+		else
+		{
+			pg_log_error("wal archive not found");
+			pg_log_error_hint("Specify the correct path using the option -w/--wal-path."
+							  "Or you must use -n/--no-parse-wal when verifying a tar-format backup.");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
@@ -787,7 +801,8 @@ verify_control_file(const char *controlpath, uint64 manifest_system_identifier)
  * close when we're done with it.
  */
 static void
-verify_tar_backup(verifier_context *context, DIR *dir)
+verify_tar_backup(verifier_context *context, DIR *dir, char **base_archive_path,
+				  char **wal_archive_path)
 {
 	struct dirent *dirent;
 	SimplePtrList tarfiles = {NULL, NULL};
@@ -816,7 +831,8 @@ verify_tar_backup(verifier_context *context, DIR *dir)
 			char	   *fullpath;
 
 			fullpath = psprintf("%s/%s", context->backup_directory, filename);
-			precheck_tar_backup_file(context, filename, fullpath, &tarfiles);
+			precheck_tar_backup_file(context, filename, fullpath, &tarfiles,
+									 base_archive_path, wal_archive_path);
 			pfree(fullpath);
 		}
 	}
@@ -875,11 +891,13 @@ verify_tar_backup(verifier_context *context, DIR *dir)
  *
  * The arguments to this function are mostly the same as the
  * verify_plain_backup_file. The additional argument outputs a list of valid
- * tar files.
+ * tar files, along with the full paths to the main archive and the WAL
+ * directory archive.
  */
 static void
 precheck_tar_backup_file(verifier_context *context, char *relpath,
-						 char *fullpath, SimplePtrList *tarfiles)
+						 char *fullpath, SimplePtrList *tarfiles,
+						 char **base_archive_path, char **wal_archive_path)
 {
 	struct stat sb;
 	Oid			tblspc_oid = InvalidOid;
@@ -918,9 +936,17 @@ precheck_tar_backup_file(verifier_context *context, char *relpath,
 	 * extension such as .gz, .lz4, or .zst.
 	 */
 	if (strncmp("base", relpath, 4) == 0)
+	{
 		suffix = relpath + 4;
+
+		*base_archive_path = pstrdup(fullpath);
+	}
 	else if (strncmp("pg_wal", relpath, 6) == 0)
+	{
 		suffix = relpath + 6;
+
+		*wal_archive_path = pstrdup(fullpath);
+	}
 	else
 	{
 		/* Expected a <tablespaceoid>.tar file here. */
diff --git a/src/bin/pg_verifybackup/t/002_algorithm.pl b/src/bin/pg_verifybackup/t/002_algorithm.pl
index ae16c11bc4d..4f284a9e828 100644
--- a/src/bin/pg_verifybackup/t/002_algorithm.pl
+++ b/src/bin/pg_verifybackup/t/002_algorithm.pl
@@ -30,10 +30,6 @@ sub test_checksums
 	{
 		# Add switch to get a tar-format backup
 		push @backup, ('--format' => 'tar');
-
-		# Add switch to skip WAL verification, which is not yet supported for
-		# tar-format backups
-		push @verify, ('--no-parse-wal');
 	}
 
 	# A backup with a bogus algorithm should fail.
diff --git a/src/bin/pg_verifybackup/t/003_corruption.pl b/src/bin/pg_verifybackup/t/003_corruption.pl
index 1dd60f709cf..f1ebdbb46b4 100644
--- a/src/bin/pg_verifybackup/t/003_corruption.pl
+++ b/src/bin/pg_verifybackup/t/003_corruption.pl
@@ -193,10 +193,8 @@ for my $scenario (@scenario)
 			command_ok([ $tar, '-cf' => "$tar_backup_path/base.tar", '.' ]);
 			chdir($cwd) || die "chdir: $!";
 
-			# Now check that the backup no longer verifies. We must use -n
-			# here, because pg_waldump can't yet read WAL from a tarfile.
 			command_fails_like(
-				[ 'pg_verifybackup', '--no-parse-wal', $tar_backup_path ],
+				[ 'pg_verifybackup', $tar_backup_path ],
 				$scenario->{'fails_like'},
 				"corrupt backup fails verification: $name");
 
diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index bc3d6b352ad..09079a94fee 100644
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -47,7 +47,6 @@ my $tsoid = $primary->safe_psql(
 		SELECT oid FROM pg_tablespace WHERE spcname = 'regress_ts1'));
 
 my $backup_path = $primary->backup_dir . '/server-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -123,14 +122,12 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
 		rmtree($backup_path);
-		rmtree($extract_path);
 	}
 }
 
diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index b62faeb5acf..5b0e76ee69d 100644
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -32,7 +32,6 @@ print $jf $junk_data;
 close $jf;
 
 my $backup_path = $primary->backup_dir . '/client-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -137,13 +136,11 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
-		rmtree($extract_path);
 		rmtree($backup_path);
 	}
 }
-- 
2.47.1

From 1713593f78bb7799ef278424b0efa56acef8bfba Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 24 Jun 2025 11:33:20 +0530
Subject: [PATCH v8 1/8] Refactor: pg_waldump: Move some declarations to new
 pg_waldump.h

This change prepares for a second source file in this directory to
support reading WAL from tar files. Common structures, declarations,
and functions are being exported through this include file so
they can be used in both files.
---
 src/bin/pg_waldump/pg_waldump.c | 11 ++---------
 src/bin/pg_waldump/pg_waldump.h | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 9 deletions(-)
 create mode 100644 src/bin/pg_waldump/pg_waldump.h

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index c6d6ba79e44..5846ee24f46 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -29,6 +29,7 @@
 #include "common/logging.h"
 #include "common/relpath.h"
 #include "getopt_long.h"
+#include "pg_waldump.h"
 #include "rmgrdesc.h"
 #include "storage/bufpage.h"
 
@@ -39,19 +40,11 @@
 
 static const char *progname;
 
-static int	WalSegSz;
+int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 static volatile sig_atomic_t time_to_stop = false;
 
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
-typedef struct XLogDumpPrivate
-{
-	TimeLineID	timeline;
-	XLogRecPtr	startptr;
-	XLogRecPtr	endptr;
-	bool		endptr_reached;
-} XLogDumpPrivate;
-
 typedef struct XLogDumpConfig
 {
 	/* display options */
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
new file mode 100644
index 00000000000..9e62b64ead5
--- /dev/null
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -0,0 +1,27 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_waldump.h - decode and display WAL
+ *
+ * Copyright (c) 2013-2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  src/bin/pg_waldump/pg_waldump.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_WALDUMP_H
+#define PG_WALDUMP_H
+
+#include "access/xlogdefs.h"
+
+extern int	WalSegSz;
+
+/* Contains the necessary information to drive WAL decoding */
+typedef struct XLogDumpPrivate
+{
+	TimeLineID	timeline;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
+	bool		endptr_reached;
+} XLogDumpPrivate;
+
+#endif		/* end of PG_WALDUMP_H */
-- 
2.47.1

From c5ce68512a54b7f586b458374f689df406f39ad6 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 26 Jun 2025 11:42:53 +0530
Subject: [PATCH v8 2/8] Refactor: pg_waldump: Separate logic used to calculate
 the required read size.

This refactoring prepares the codebase for an upcoming patch that will
support reading WAL from tar files. The logic for calculating the
required read size has been updated to handle both normal WAL files
and WAL files located inside a tar archive.
---
 src/bin/pg_waldump/pg_waldump.c | 39 ++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 5846ee24f46..0dc28ea360c 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -326,6 +326,29 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/* Returns the size in bytes of the data to be read. */
+static inline int
+required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
+				  int reqLen)
+{
+	int			count = XLOG_BLCKSZ;
+
+	if (XLogRecPtrIsValid(private->endptr))
+	{
+		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
+			count = XLOG_BLCKSZ;
+		else if (targetPagePtr + reqLen <= private->endptr)
+			count = private->endptr - targetPagePtr;
+		else
+		{
+			private->endptr_reached = true;
+			return -1;
+		}
+	}
+
+	return count;
+}
+
 /* pg_waldump's XLogReaderRoutine->segment_open callback */
 static void
 WALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
@@ -383,21 +406,11 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = XLOG_BLCKSZ;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
-	if (XLogRecPtrIsValid(private->endptr))
-	{
-		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
-			count = XLOG_BLCKSZ;
-		else if (targetPagePtr + reqLen <= private->endptr)
-			count = private->endptr - targetPagePtr;
-		else
-		{
-			private->endptr_reached = true;
-			return -1;
-		}
-	}
+	if (private->endptr_reached)
+		return -1;
 
 	if (!WALRead(state, readBuff, targetPagePtr, count, private->timeline,
 				 &errinfo))
-- 
2.47.1

From e0a2296c0b79bf3e2c62c712829c9aaa0b516334 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 30 Jul 2025 12:43:30 +0530
Subject: [PATCH v8 3/8] Refactor: pg_waldump: Restructure TAP tests.

Restructured some tests to run inside a loop, facilitating their
re-execution for decoding WAL from tar archives.
---
 src/bin/pg_waldump/t/001_basic.pl | 123 ++++++++++++++++--------------
 1 file changed, 67 insertions(+), 56 deletions(-)

diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index f26d75e01cf..1b712e8d74d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -198,28 +198,6 @@ command_like(
 	],
 	qr/./,
 	'runs with start and end segment specified');
-command_fails_like(
-	[ 'pg_waldump', '--path' => $node->data_dir ],
-	qr/error: no start WAL location given/,
-	'path option requires start location');
-command_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-		'--end' => $end_lsn,
-	],
-	qr/./,
-	'runs with path option and start and end locations');
-command_fails_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-	],
-	qr/error: error in WAL record at/,
-	'falling off the end of the WAL results in an error');
-
 command_like(
 	[
 		'pg_waldump', '--quiet',
@@ -227,15 +205,6 @@ command_like(
 	],
 	qr/^$/,
 	'no output with --quiet option');
-command_fails_like(
-	[
-		'pg_waldump', '--quiet',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn
-	],
-	qr/error: error in WAL record at/,
-	'errors are shown with --quiet');
-
 
 # Test for: Display a message that we're skipping data if `from`
 # wasn't a pointer to the start of a record.
@@ -272,7 +241,6 @@ sub test_pg_waldump
 
 	my $result = IPC::Run::run [
 		'pg_waldump',
-		'--path' => $node->data_dir,
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
 		@opts
@@ -288,38 +256,81 @@ sub test_pg_waldump
 
 my @lines;
 
-@lines = test_pg_waldump;
-is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
+my @scenario = (
+	{
+		'path' => $node->data_dir
+	});
 
-@lines = test_pg_waldump('--limit' => 6);
-is(@lines, 6, 'limit option observed');
+for my $scenario (@scenario)
+{
+	my $path = $scenario->{'path'};
 
-@lines = test_pg_waldump('--fullpage');
-is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
+	SKIP:
+	{
+		command_fails_like(
+			[ 'pg_waldump', '--path' => $path ],
+			qr/error: no start WAL location given/,
+			'path option requires start location');
+		command_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+				'--end' => $end_lsn,
+			],
+			qr/./,
+			'runs with path option and start and end locations');
+		command_fails_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+			],
+			qr/error: error in WAL record at/,
+			'falling off the end of the WAL results in an error');
 
-@lines = test_pg_waldump('--stats');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		command_fails_like(
+			[
+				'pg_waldump', '--quiet',
+				'--path' => $path,
+				'--start' => $start_lsn
+			],
+			qr/error: error in WAL record at/,
+			'errors are shown with --quiet');
 
-@lines = test_pg_waldump('--stats=record');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		@lines = test_pg_waldump('--path' => $path);
+		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-@lines = test_pg_waldump('--rmgr' => 'Btree');
-is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		is(@lines, 6, 'limit option observed');
 
-@lines = test_pg_waldump('--fork' => 'init');
-is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
-is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
-	0, 'only lines for selected relation');
+		@lines = test_pg_waldump('--path' => $path, '--stats');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
-	'--block' => 1);
-is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
+		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+
+		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
+		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
+			0, 'only lines for selected relation');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
+			'--block' => 1);
+		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+	}
+}
 
 done_testing();
-- 
2.47.1

From 7686e875c9da4cedafb884dd4cd153d35c96d540 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 5 Nov 2025 15:40:36 +0530
Subject: [PATCH v8 4/8] pg_waldump: Add support for archived WAL decoding.

pg_waldump can now accept the path to a tar archive containing WAL
files and decode them. This feature was added primarily for
pg_verifybackup, which previously disabled WAL parsing for
tar-formatted backups.

Note that this patch requires that the WAL files within the archive be
in sequential order; an error will be reported otherwise. The next
patch is planned to remove this restriction.
---
 doc/src/sgml/ref/pg_waldump.sgml     |   8 +-
 src/bin/pg_waldump/Makefile          |   7 +-
 src/bin/pg_waldump/archive_waldump.c | 589 +++++++++++++++++++++++++++
 src/bin/pg_waldump/meson.build       |   4 +-
 src/bin/pg_waldump/pg_waldump.c      | 215 +++++++---
 src/bin/pg_waldump/pg_waldump.h      |  36 +-
 src/bin/pg_waldump/t/001_basic.pl    |  84 +++-
 src/tools/pgindent/typedefs.list     |   3 +
 8 files changed, 870 insertions(+), 76 deletions(-)
 create mode 100644 src/bin/pg_waldump/archive_waldump.c

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index ce23add5577..d004bb0f67e 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -141,13 +141,17 @@ PostgreSQL documentation
       <term><option>--path=<replaceable>path</replaceable></option></term>
       <listitem>
        <para>
-        Specifies a directory to search for WAL segment files or a
-        directory with a <literal>pg_wal</literal> subdirectory that
+        Specifies a tar archive or a directory to search for WAL segment files
+        or a directory with a <literal>pg_wal</literal> subdirectory that
         contains such files.  The default is to search in the current
         directory, the <literal>pg_wal</literal> subdirectory of the
         current directory, and the <literal>pg_wal</literal> subdirectory
         of <envar>PGDATA</envar>.
        </para>
+       <para>
+        If a tar archive is provided, its WAL segment files must be in
+        sequential order; otherwise, an error will be reported.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index 4c1ee649501..05ac5763a57 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -3,6 +3,9 @@
 PGFILEDESC = "pg_waldump - decode and display WAL"
 PGAPPICON=win32
 
+# make these available to TAP test scripts
+export TAR
+
 subdir = src/bin/pg_waldump
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
@@ -12,11 +15,13 @@ OBJS = \
 	$(WIN32RES) \
 	compat.o \
 	pg_waldump.o \
+	archive_waldump.o \
 	rmgrdesc.o \
 	xlogreader.o \
 	xlogstats.o
 
-override CPPFLAGS := -DFRONTEND $(CPPFLAGS)
+override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
new file mode 100644
index 00000000000..f991633e58c
--- /dev/null
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -0,0 +1,589 @@
+/*-------------------------------------------------------------------------
+ *
+ * archive_waldump.c
+ *		A generic facility for reading WAL data from tar archives via archive
+ *		streamer.
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/bin/pg_waldump/archive_waldump.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <unistd.h>
+
+#include "access/xlog_internal.h"
+#include "common/hashfn.h"
+#include "common/logging.h"
+#include "fe_utils/simple_list.h"
+#include "pg_waldump.h"
+
+/*
+ * How many bytes should we try to read from a file at once?
+ */
+#define READ_CHUNK_SIZE				(128 * 1024)
+
+/* Structure for storing the WAL segment data from the archive */
+typedef struct ArchivedWALEntry
+{
+	uint32		status;			/* hash status */
+	XLogSegNo	segno;			/* hash key: WAL segment number */
+	TimeLineID	timeline;		/* timeline of this wal file */
+
+	StringInfoData buf;
+	bool		tmpseg_exists;	/* spill file exists? */
+
+	int			total_read;		/* total read of this WAL segment, including
+								 * buffered and temporarily written data */
+} ArchivedWALEntry;
+
+#define SH_PREFIX				ArchivedWAL
+#define SH_ELEMENT_TYPE			ArchivedWALEntry
+#define SH_KEY_TYPE				XLogSegNo
+#define SH_KEY					segno
+#define SH_HASH_KEY(tb, key)	murmurhash64((uint64) key)
+#define SH_EQUAL(tb, a, b)		(a == b)
+#define SH_GET_HASH(tb, a)		a->hash
+#define SH_SCOPE				static inline
+#define SH_RAW_ALLOCATOR		pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static ArchivedWAL_hash *ArchivedWAL_HTAB = NULL;
+
+typedef struct astreamer_waldump
+{
+	astreamer	base;
+	XLogDumpPrivate *privateInfo;
+} astreamer_waldump;
+
+static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
+static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
+											   XLogDumpPrivate *privateInfo);
+
+static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
+static void astreamer_waldump_content(astreamer *streamer,
+									  astreamer_member *member,
+									  const char *data, int len,
+									  astreamer_archive_context context);
+static void astreamer_waldump_finalize(astreamer *streamer);
+static void astreamer_waldump_free(astreamer *streamer);
+
+static bool member_is_wal_file(astreamer_waldump *mystreamer,
+							   astreamer_member *member,
+							   XLogSegNo *curSegNo,
+							   TimeLineID *curTimeline);
+
+static const astreamer_ops astreamer_waldump_ops = {
+	.content = astreamer_waldump_content,
+	.finalize = astreamer_waldump_finalize,
+	.free = astreamer_waldump_free
+};
+
+/*
+ * Returns true if the given file is a tar archive and outputs its compression
+ * algorithm.
+ */
+bool
+is_archive_file(const char *fname, pg_compress_algorithm *compression)
+{
+	int			fname_len = strlen(fname);
+	pg_compress_algorithm compress_algo;
+
+	/* Now, check the compression type of the tar */
+	if (fname_len > 4 &&
+		strcmp(fname + fname_len - 4, ".tar") == 0)
+		compress_algo = PG_COMPRESSION_NONE;
+	else if (fname_len > 4 &&
+			 strcmp(fname + fname_len - 4, ".tgz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 7 &&
+			 strcmp(fname + fname_len - 7, ".tar.gz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.lz4") == 0)
+		compress_algo = PG_COMPRESSION_LZ4;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.zst") == 0)
+		compress_algo = PG_COMPRESSION_ZSTD;
+	else
+		return false;
+
+	*compression = compress_algo;
+
+	return true;
+}
+
+/*
+ * Initializes the tar archive reader to read WAL files from the archive,
+ * creates a hash table to store them, performs quick existence checks for WAL
+ * entries in the archive and retrieves the WAL segment size, and sets up
+ * filtering criteria for relevant entries.
+ */
+void
+init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
+					pg_compress_algorithm compression)
+{
+	int			fd;
+	astreamer  *streamer;
+	ArchivedWALEntry *entry = NULL;
+	XLogLongPageHeader longhdr;
+
+	/* Open tar archive and store its file descriptor */
+	fd = open_file_in_directory(waldir, privateInfo->archive_name);
+
+	if (fd < 0)
+		pg_fatal("could not open file \"%s\"", privateInfo->archive_name);
+
+	privateInfo->archive_fd = fd;
+
+	streamer = astreamer_waldump_new(privateInfo);
+
+	/* Before that we must parse the tar archive. */
+	streamer = astreamer_tar_parser_new(streamer);
+
+	/* Before that we must decompress, if archive is compressed. */
+	if (compression == PG_COMPRESSION_GZIP)
+		streamer = astreamer_gzip_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_LZ4)
+		streamer = astreamer_lz4_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_ZSTD)
+		streamer = astreamer_zstd_decompressor_new(streamer);
+
+	privateInfo->archive_streamer = streamer;
+
+	/* Hash table storing WAL entries read from the archive */
+	ArchivedWAL_HTAB = ArchivedWAL_create(16, NULL);
+
+	/*
+	 * Verify that the archive contains valid WAL files and fetch WAL segment
+	 * size
+	 */
+	while (entry == NULL || entry->buf.len < XLOG_BLCKSZ)
+	{
+		if (read_archive_file(privateInfo, XLOG_BLCKSZ) == 0)
+			pg_fatal("could not find WAL in \"%s\" archive",
+					 privateInfo->archive_name);
+
+		entry = privateInfo->cur_wal;
+	}
+
+	/* Set WalSegSz if WAL data is successfully read */
+	longhdr = (XLogLongPageHeader) entry->buf.data;
+
+	WalSegSz = longhdr->xlp_seg_size;
+
+	if (!IsValidWalSegSize(WalSegSz))
+	{
+		pg_log_error(ngettext("invalid WAL segment size in WAL file from archive \"%s\" (%d byte)",
+							  "invalid WAL segment size in WAL file from archive \"%s\" (%d bytes)",
+							  WalSegSz),
+					 privateInfo->archive_name, WalSegSz);
+		pg_log_error_detail("The WAL segment size must be a power of two between 1 MB and 1 GB.");
+		exit(1);
+	}
+
+	/*
+	 * With the WAL segment size available, we can now initialize the
+	 * dependent start and end segment numbers.
+	 */
+	Assert(!XLogRecPtrIsInvalid(privateInfo->startptr));
+	XLByteToSeg(privateInfo->startptr, privateInfo->startSegNo, WalSegSz);
+
+	if (XLogRecPtrIsInvalid(privateInfo->endptr))
+		privateInfo->endSegNo = UINT64_MAX;
+	else
+		XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+}
+
+/*
+ * Release the archive streamer chain and close the archive file.
+ */
+void
+free_archive_reader(XLogDumpPrivate *privateInfo)
+{
+	/*
+	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
+	 * flush any remaining buffered data or to ensure the end of the tar
+	 * archive is reached. However, when decoding a WAL file, once we hit the
+	 * end LSN, any remaining WAL data in the buffer or the tar archive's
+	 * unreached end can be safely ignored.
+	 */
+	astreamer_free(privateInfo->archive_streamer);
+
+	/* Close the file. */
+	if (close(privateInfo->archive_fd) != 0)
+		pg_log_error("could not close file \"%s\": %m",
+					 privateInfo->archive_name);
+}
+
+/*
+ * Copies WAL data from astreamer to readBuff; if unavailable, fetches more
+ * from the tar archive via astreamer.
+ */
+int
+read_archive_wal_page(XLogDumpPrivate *privateInfo, XLogRecPtr targetPagePtr,
+					  Size count, char *readBuff)
+{
+	char	   *p = readBuff;
+	Size		nbytes = count;
+	XLogRecPtr	recptr = targetPagePtr;
+	XLogSegNo	segno;
+	ArchivedWALEntry *entry;
+
+	XLByteToSeg(targetPagePtr, segno, WalSegSz);
+	entry = get_archive_wal_entry(segno, privateInfo);
+
+	while (nbytes > 0)
+	{
+		char	   *buf = entry->buf.data;
+		int			len = entry->buf.len;
+
+		/* WAL record range that the buffer contains */
+		XLogRecPtr	endPtr;
+		XLogRecPtr	startPtr;
+
+		XLogSegNoOffsetToRecPtr(entry->segno, entry->total_read,
+								WalSegSz, endPtr);
+		startPtr = endPtr - len;
+
+		/*
+		 * pg_waldump may request to re-read the currently active page, but
+		 * never a page older than the current one. Therefore, any fully
+		 * consumed WAL data preceding the current page can be safely
+		 * discarded.
+		 */
+		if (recptr >= endPtr)
+		{
+			/* Discard the buffered data */
+			resetStringInfo(&entry->buf);
+			len = 0;
+
+			/*
+			 * Push back the partial page data for the current page to the
+			 * buffer, ensuring it remains available for re-reading if
+			 * requested.
+			 */
+			if (p > readBuff)
+			{
+				Assert((count - nbytes) > 0);
+				appendBinaryStringInfo(&entry->buf, readBuff, count - nbytes);
+			}
+		}
+
+		if (len > 0 && recptr > startPtr)
+		{
+			int			skipBytes = 0;
+
+			/*
+			 * The required offset is not at the start of the buffer, so skip
+			 * bytes until reaching the desired offset of the target page.
+			 */
+			skipBytes = recptr - startPtr;
+
+			buf += skipBytes;
+			len -= skipBytes;
+		}
+
+		if (len > 0)
+		{
+			int			readBytes = len >= nbytes ? nbytes : len;
+
+			/* Ensure the reading page is in the buffer */
+			Assert(recptr >= startPtr && recptr < endPtr);
+
+			memcpy(p, buf, readBytes);
+
+			/* Update state for read */
+			nbytes -= readBytes;
+			p += readBytes;
+			recptr += readBytes;
+		}
+		else
+		{
+			/*
+			 * Fetch more data; raise an error if it's not the current segment
+			 * being read by the archive streamer or if reading of the
+			 * archived file has finished.
+			 */
+			if (privateInfo->cur_wal != entry ||
+				read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+			{
+				char		fname[MAXFNAMELEN];
+
+				XLogFileName(fname, privateInfo->timeline, entry->segno,
+							 WalSegSz);
+				pg_fatal("could not read file \"%s\" from archive \"%s\": read %lld of %lld",
+						 fname, privateInfo->archive_name,
+						 (long long int) count - nbytes,
+						 (long long int) nbytes);
+			}
+		}
+	}
+
+	/*
+	 * Should have either have successfully read all the requested bytes or
+	 * reported a failure before this point.
+	 */
+	Assert(nbytes == 0);
+
+	/*
+	 * NB: We return the fixed value provided as input. Although we could
+	 * return a boolean since we either successfully read the WAL page or
+	 * raise an error, but the caller expects this value to be returned. The
+	 * routine that reads WAL pages from the physical WAL file follows the
+	 * same convention.
+	 */
+	return count;
+}
+
+/*
+ * Reads the archive file and passes it to the archive streamer for
+ * decompression.
+ */
+static int
+read_archive_file(XLogDumpPrivate *privateInfo, Size count)
+{
+	int			rc;
+	char	   *buffer;
+
+	buffer = pg_malloc(READ_CHUNK_SIZE * sizeof(uint8));
+
+	rc = read(privateInfo->archive_fd, buffer, count);
+	if (rc < 0)
+		pg_fatal("could not read file \"%s\": %m",
+				 privateInfo->archive_name);
+
+	/*
+	 * Decompress (if required), and then parse the previously read contents
+	 * of the tar file.
+	 */
+	if (rc > 0)
+		astreamer_content(privateInfo->archive_streamer, NULL,
+						  buffer, rc, ASTREAMER_UNKNOWN);
+	pg_free(buffer);
+
+	return rc;
+}
+
+/*
+ * Returns the archived WAL entry from the hash table if it exists. Otherwise,
+ * it invokes the routine to read the archived file and retrieve the entry if
+ * it is not already in hash table.
+ */
+static ArchivedWALEntry *
+get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
+{
+	ArchivedWALEntry *entry = NULL;
+	char		fname[MAXFNAMELEN];
+
+	/* Search hash table */
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry != NULL)
+		return entry;
+
+	/* Needed WAL yet to be decoded from archive, do the same */
+	while (1)
+	{
+		entry = privateInfo->cur_wal;
+
+		/* Fetch more data */
+		if (entry == NULL || entry->buf.len == 0)
+		{
+			if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+				break;			/* archive file ended */
+		}
+
+		/*
+		 * Either, here for the first time, or the archived streamer is
+		 * reading a non-WAL file or an irrelevant WAL file.
+		 */
+		if (entry == NULL)
+			continue;
+
+		/* Found the required entry */
+		if (entry->segno == segno)
+			return entry;
+
+		/*
+		 * Ignore if the timeline is different or the current segment is not
+		 * the desired one.
+		 */
+		if (privateInfo->timeline != entry->timeline ||
+			privateInfo->startSegNo > entry->segno ||
+			privateInfo->endSegNo < entry->segno)
+		{
+			privateInfo->cur_wal = NULL;
+			continue;
+		}
+
+		/* WAL segments must be archived in order */
+		pg_log_error("WAL files are not archived in sequential order");
+		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
+							segno, entry->segno);
+		exit(1);
+	}
+
+	/* Requested WAL segment not found */
+	XLogFileName(fname, privateInfo->timeline, segno, WalSegSz);
+	pg_fatal("could not find file \"%s\" in archive", fname);
+}
+
+/*
+ * Create an astreamer that can read WAL from tar file.
+ */
+static astreamer *
+astreamer_waldump_new(XLogDumpPrivate *privateInfo)
+{
+	astreamer_waldump *streamer;
+
+	streamer = palloc0(sizeof(astreamer_waldump));
+	*((const astreamer_ops **) &streamer->base.bbs_ops) =
+		&astreamer_waldump_ops;
+
+	streamer->privateInfo = privateInfo;
+
+	return &streamer->base;
+}
+
+/*
+ * Main entry point of the archive streamer for reading WAL data from a tar
+ * file. If a member is identified as a valid WAL file, a hash entry is created
+ * for it, and its contents are copied into that entry's buffer, making them
+ * accessible to the decoding routine.
+ */
+static void
+astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
+						  const char *data, int len,
+						  astreamer_archive_context context)
+{
+	astreamer_waldump *mystreamer = (astreamer_waldump *) streamer;
+	XLogDumpPrivate *privateInfo = mystreamer->privateInfo;
+
+	Assert(context != ASTREAMER_UNKNOWN);
+
+	switch (context)
+	{
+		case ASTREAMER_MEMBER_HEADER:
+			{
+				XLogSegNo	segno;
+				TimeLineID	timeline;
+				ArchivedWALEntry *entry;
+				bool		found;
+
+				pg_log_debug("reading \"%s\"", member->pathname);
+
+				if (!member_is_wal_file(mystreamer, member,
+										&segno, &timeline))
+					break;
+
+				entry = ArchivedWAL_insert(ArchivedWAL_HTAB, segno, &found);
+
+				/*
+				 * Shouldn't happen, but if it does, simply ignore the
+				 * duplicate WAL file.
+				 */
+				if (found)
+				{
+					pg_log_warning("ignoring duplicate WAL file found in archive: \"%s\"",
+								   member->pathname);
+					break;
+				}
+
+				initStringInfo(&entry->buf);
+				entry->timeline = timeline;
+				entry->total_read = 0;
+
+				privateInfo->cur_wal = entry;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_CONTENTS:
+			if (privateInfo->cur_wal)
+			{
+				appendBinaryStringInfo(&privateInfo->cur_wal->buf, data, len);
+				privateInfo->cur_wal->total_read += len;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_TRAILER:
+			privateInfo->cur_wal = NULL;
+			break;
+
+		case ASTREAMER_ARCHIVE_TRAILER:
+			break;
+
+		default:
+			/* Shouldn't happen. */
+			pg_fatal("unexpected state while parsing tar file");
+	}
+}
+
+/*
+ * End-of-stream processing for a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_finalize(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+}
+
+/*
+ * Free memory associated with a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_free(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+	pfree(streamer);
+}
+
+/*
+ * Returns true if the archive member name matches the WAL naming format. If
+ * successful, it also outputs the WAL segment number, and timeline.
+ */
+static bool
+member_is_wal_file(astreamer_waldump *mystreamer, astreamer_member *member,
+				   XLogSegNo *curSegNo, TimeLineID *curTimeline)
+{
+	int			pathlen;
+	XLogSegNo	segNo;
+	TimeLineID	timeline;
+	char	   *fname;
+
+	/* We are only interested in normal files. */
+	if (member->is_directory || member->is_link)
+		return false;
+
+	pathlen = strlen(member->pathname);
+	if (pathlen < XLOG_FNAME_LEN)
+		return false;
+
+	/* WAL file could be with full path */
+	fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+	if (!IsXLogFileName(fname))
+		return false;
+
+	/*
+	 * XXX: On some systems (e.g., OpenBSD), the tar utility includes
+	 * PaxHeaders when creating an archive. These are special entries that
+	 * store extended metadata for the file entry immediately following them,
+	 * and they share the exact same name as that file.
+	 */
+	if (strstr(member->pathname, "PaxHeaders."))
+		return false;
+
+	/* Parse position from file */
+	XLogFromFileName(fname, &timeline, &segNo, WalSegSz);
+
+	*curSegNo = segNo;
+	*curTimeline = timeline;
+
+	return true;
+}
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 937e0d68841..da00746587c 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -3,6 +3,7 @@
 pg_waldump_sources = files(
   'compat.c',
   'pg_waldump.c',
+  'archive_waldump.c',
   'rmgrdesc.c',
 )
 
@@ -18,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, lz4, zstd],
+  dependencies: [frontend_code, lz4, zstd, libpq],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
@@ -29,6 +30,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'TAR': tar.found() ? tar.full_path() : ''},
     'tests': [
       't/001_basic.pl',
       't/002_save_fullpage.pl',
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 0dc28ea360c..02ad141e44a 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -177,7 +177,7 @@ split_path(const char *path, char **dir, char **fname)
  *
  * return a read only fd
  */
-static int
+int
 open_file_in_directory(const char *directory, const char *fname)
 {
 	int			fd = -1;
@@ -436,6 +436,44 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 	return count;
 }
 
+/*
+ * pg_waldump's XLogReaderRoutine->segment_open callback to support dumping WAL
+ * files from tar archives.
+ */
+static void
+TarWALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
+					  TimeLineID *tli_p)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->segment_close callback.
+ */
+static void
+TarWALDumpCloseSegment(XLogReaderState *state)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->page_read callback to support dumping WAL
+ * files from tar archives.
+ */
+static int
+TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				   XLogRecPtr targetPtr, char *readBuff)
+{
+	XLogDumpPrivate *private = state->private_data;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
+
+	if (private->endptr_reached)
+		return -1;
+
+	/* Read the WAL page from the archive streamer */
+	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
+}
+
 /*
  * Boolean to return whether the given WAL record matches a specific relation
  * and optionally block.
@@ -773,8 +811,8 @@ usage(void)
 	printf(_("  -F, --fork=FORK        only show records that modify blocks in fork FORK;\n"
 			 "                         valid names are main, fsm, vm, init\n"));
 	printf(_("  -n, --limit=N          number of records to display\n"));
-	printf(_("  -p, --path=PATH        directory in which to find WAL segment files or a\n"
-			 "                         directory with a ./pg_wal that contains such files\n"
+	printf(_("  -p, --path=PATH        tar archive or a directory in which to find WAL segment files or\n"
+			 "                         a directory with a ./pg_wal that contains such files\n"
 			 "                         (default: current directory, ./pg_wal, $PGDATA/pg_wal)\n"));
 	printf(_("  -q, --quiet            do not print any output, except for errors\n"));
 	printf(_("  -r, --rmgr=RMGR        only show records generated by resource manager RMGR;\n"
@@ -806,7 +844,10 @@ main(int argc, char **argv)
 	XLogRecord *record;
 	XLogRecPtr	first_record;
 	char	   *waldir = NULL;
+	char	   *walpath = NULL;
 	char	   *errormsg;
+	bool		is_archive = false;
+	pg_compress_algorithm compression;
 
 	static struct option long_options[] = {
 		{"bkp-details", no_argument, NULL, 'b'},
@@ -938,7 +979,7 @@ main(int argc, char **argv)
 				}
 				break;
 			case 'p':
-				waldir = pg_strdup(optarg);
+				walpath = pg_strdup(optarg);
 				break;
 			case 'q':
 				config.quiet = true;
@@ -1102,10 +1143,20 @@ main(int argc, char **argv)
 		goto bad_argument;
 	}
 
-	if (waldir != NULL)
+	if (walpath != NULL)
 	{
+		/* validate path points to tar archive */
+		if (is_archive_file(walpath, &compression))
+		{
+			char	   *fname = NULL;
+
+			split_path(walpath, &waldir, &fname);
+
+			private.archive_name = fname;
+			is_archive = true;
+		}
 		/* validate path points to directory */
-		if (!verify_directory(waldir))
+		else if (!verify_directory(walpath))
 		{
 			pg_log_error("could not open directory \"%s\": %m", waldir);
 			goto bad_argument;
@@ -1123,6 +1174,17 @@ main(int argc, char **argv)
 		int			fd;
 		XLogSegNo	segno;
 
+		/*
+		 * If a tar archive is passed using the --path option, all other
+		 * arguments become unnecessary.
+		 */
+		if (is_archive)
+		{
+			pg_log_error("unnecessary command-line arguments specified with tar archive (first is \"%s\")",
+						 argv[optind]);
+			goto bad_argument;
+		}
+
 		split_path(argv[optind], &directory, &fname);
 
 		if (waldir == NULL && directory != NULL)
@@ -1133,69 +1195,77 @@ main(int argc, char **argv)
 				pg_fatal("could not open directory \"%s\": %m", waldir);
 		}
 
-		waldir = identify_target_directory(waldir, fname);
-		fd = open_file_in_directory(waldir, fname);
-		if (fd < 0)
-			pg_fatal("could not open file \"%s\"", fname);
-		close(fd);
-
-		/* parse position from file */
-		XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
-
-		if (!XLogRecPtrIsValid(private.startptr))
-			XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
-		else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+		if (fname != NULL && is_archive_file(fname, &compression))
 		{
-			pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.startptr),
-						 fname);
-			goto bad_argument;
+			private.archive_name = fname;
+			is_archive = true;
 		}
-
-		/* no second file specified, set end position */
-		if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
-			XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
-
-		/* parse ENDSEG if passed */
-		if (optind + 1 < argc)
+		else
 		{
-			XLogSegNo	endsegno;
-
-			/* ignore directory, already have that */
-			split_path(argv[optind + 1], &directory, &fname);
-
+			waldir = identify_target_directory(waldir, fname);
 			fd = open_file_in_directory(waldir, fname);
 			if (fd < 0)
 				pg_fatal("could not open file \"%s\"", fname);
 			close(fd);
 
 			/* parse position from file */
-			XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+			XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
 
-			if (endsegno < segno)
-				pg_fatal("ENDSEG %s is before STARTSEG %s",
-						 argv[optind + 1], argv[optind]);
+			if (!XLogRecPtrIsValid(private.startptr))
+				XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
+			else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+			{
+				pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.startptr),
+							 fname);
+				goto bad_argument;
+			}
 
-			if (!XLogRecPtrIsValid(private.endptr))
-				XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
-										private.endptr);
+			/* no second file specified, set end position */
+			if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
+				XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
 
-			/* set segno to endsegno for check of --end */
-			segno = endsegno;
-		}
+			/* parse ENDSEG if passed */
+			if (optind + 1 < argc)
+			{
+				XLogSegNo	endsegno;
 
+				/* ignore directory, already have that */
+				split_path(argv[optind + 1], &directory, &fname);
 
-		if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
-			private.endptr != (segno + 1) * WalSegSz)
-		{
-			pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.endptr),
-						 argv[argc - 1]);
-			goto bad_argument;
+				fd = open_file_in_directory(waldir, fname);
+				if (fd < 0)
+					pg_fatal("could not open file \"%s\"", fname);
+				close(fd);
+
+				/* parse position from file */
+				XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+
+				if (endsegno < segno)
+					pg_fatal("ENDSEG %s is before STARTSEG %s",
+							 argv[optind + 1], argv[optind]);
+
+				if (!XLogRecPtrIsValid(private.endptr))
+					XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
+											private.endptr);
+
+				/* set segno to endsegno for check of --end */
+				segno = endsegno;
+			}
+
+
+			if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
+				private.endptr != (segno + 1) * WalSegSz)
+			{
+				pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.endptr),
+							 argv[argc - 1]);
+				goto bad_argument;
+			}
 		}
 	}
-	else
-		waldir = identify_target_directory(waldir, NULL);
+	else if (!is_archive)
+		waldir = identify_target_directory(walpath, NULL);
 
 	/* we don't know what to print */
 	if (!XLogRecPtrIsValid(private.startptr))
@@ -1207,12 +1277,36 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
-	xlogreader_state =
-		XLogReaderAllocate(WalSegSz, waldir,
-						   XL_ROUTINE(.page_read = WALDumpReadPage,
-									  .segment_open = WALDumpOpenSegment,
-									  .segment_close = WALDumpCloseSegment),
-						   &private);
+	if (is_archive)
+	{
+		/*
+		 * A NULL WAL directory indicates that the archive file is located
+		 * in the current working directory of the pg_waldump execution
+		 */
+		waldir = waldir ? pg_strdup(waldir) : pg_strdup(".");
+
+		/* Set up for reading tar file */
+		init_archive_reader(&private, waldir, compression);
+
+		/* Routine to decode WAL files in tar archive */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = TarWALDumpReadPage,
+										  .segment_open = TarWALDumpOpenSegment,
+										  .segment_close = TarWALDumpCloseSegment),
+							   &private);
+	}
+	else
+	{
+		/* Routine to decode WAL files */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = WALDumpReadPage,
+										  .segment_open = WALDumpOpenSegment,
+										  .segment_close = WALDumpCloseSegment),
+							   &private);
+	}
+
 	if (!xlogreader_state)
 		pg_fatal("out of memory while allocating a WAL reading processor");
 
@@ -1321,6 +1415,9 @@ main(int argc, char **argv)
 
 	XLogReaderFree(xlogreader_state);
 
+	if (is_archive)
+		free_archive_reader(&private);
+
 	return EXIT_SUCCESS;
 
 bad_argument:
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 9e62b64ead5..54758c3548a 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -12,9 +12,13 @@
 #define PG_WALDUMP_H
 
 #include "access/xlogdefs.h"
+#include "fe_utils/astreamer.h"
 
 extern int	WalSegSz;
 
+/* Forward declaration */
+struct ArchivedWALEntry;
+
 /* Contains the necessary information to drive WAL decoding */
 typedef struct XLogDumpPrivate
 {
@@ -22,6 +26,36 @@ typedef struct XLogDumpPrivate
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	bool		endptr_reached;
+
+	/* Fields required to read WAL from archive */
+	char	   *archive_name;	/* Tar archive name */
+	int			archive_fd;		/* File descriptor for the open tar file */
+
+	astreamer  *archive_streamer;
+
+	/* What the archive streamer is currently reading */
+	struct ArchivedWALEntry *cur_wal;
+
+	/*
+	 * Although these values can be easily derived from startptr and endptr,
+	 * doing so repeatedly for each archived member would be inefficient, as
+	 * it would involve recalculating and filtering out irrelevant WAL
+	 * segments.
+	 */
+	XLogSegNo	startSegNo;
+	XLogSegNo	endSegNo;
 } XLogDumpPrivate;
 
-#endif		/* end of PG_WALDUMP_H */
+extern int	open_file_in_directory(const char *directory, const char *fname);
+
+extern bool is_archive_file(const char *fname,
+							pg_compress_algorithm *compression);
+extern void init_archive_reader(XLogDumpPrivate *privateInfo,
+								const char *waldir,
+								pg_compress_algorithm compression);
+extern void free_archive_reader(XLogDumpPrivate *privateInfo);
+extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
+								  XLogRecPtr targetPagePtr,
+								  Size count, char *readBuff);
+
+#endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 1b712e8d74d..443126a9ce6 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -3,10 +3,13 @@
 
 use strict;
 use warnings FATAL => 'all';
+use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
 
+my $tar = $ENV{TAR};
+
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
 program_options_handling_ok('pg_waldump');
@@ -235,7 +238,7 @@ command_like(
 sub test_pg_waldump
 {
 	local $Test::Builder::Level = $Test::Builder::Level + 1;
-	my @opts = @_;
+	my ($path, @opts) = @_;
 
 	my ($stdout, $stderr);
 
@@ -243,6 +246,7 @@ sub test_pg_waldump
 		'pg_waldump',
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
+		'--path' => $path,
 		@opts
 	  ],
 	  '>' => \$stdout,
@@ -254,11 +258,50 @@ sub test_pg_waldump
 	return @lines;
 }
 
-my @lines;
+# Create a tar archive, sorting the file order
+sub generate_archive
+{
+	my ($archive, $directory, $compression_flags) = @_;
+
+	my @files;
+	opendir my $dh, $directory or die "opendir: $!";
+	while (my $entry = readdir $dh) {
+		# Skip '.' and '..'
+		next if $entry eq '.' || $entry eq '..';
+		push @files, $entry;
+	}
+	closedir $dh;
+
+	@files = sort @files;
+
+	# move into the WAL directory before archiving files
+	my $cwd = getcwd;
+	chdir($directory) || die "chdir: $!";
+	command_ok([$tar, $compression_flags, $archive, @files]);
+	chdir($cwd) || die "chdir: $!";
+}
+
+my $tmp_dir = PostgreSQL::Test::Utils::tempdir_short();
 
 my @scenario = (
 	{
-		'path' => $node->data_dir
+		'path' => $node->data_dir,
+		'is_archive' => 0,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar",
+		'compression_method' => 'none',
+		'compression_flags' => '-cf',
+		'is_archive' => 1,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar.gz",
+		'compression_method' => 'gzip',
+		'compression_flags' => '-czf',
+		'is_archive' => 1,
+		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
 	});
 
 for my $scenario (@scenario)
@@ -267,6 +310,19 @@ for my $scenario (@scenario)
 
 	SKIP:
 	{
+		skip "tar command is not available", 3
+		  if !defined $tar;
+		skip "$scenario->{'compression_method'} compression not supported by this build", 3
+		  if !$scenario->{'enabled'} && $scenario->{'is_archive'};
+
+		  # create pg_wal archive
+		  if ($scenario->{'is_archive'})
+		  {
+			  generate_archive($path,
+				  $node->data_dir . '/pg_wal',
+				  $scenario->{'compression_flags'});
+		  }
+
 		command_fails_like(
 			[ 'pg_waldump', '--path' => $path ],
 			qr/error: no start WAL location given/,
@@ -298,38 +354,42 @@ for my $scenario (@scenario)
 			qr/error: error in WAL record at/,
 			'errors are shown with --quiet');
 
-		@lines = test_pg_waldump('--path' => $path);
+		my @lines;
+		@lines = test_pg_waldump($path);
 		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		@lines = test_pg_waldump($path, '--limit' => 6);
 		is(@lines, 6, 'limit option observed');
 
-		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		@lines = test_pg_waldump($path, '--fullpage');
 		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats');
+		@lines = test_pg_waldump($path, '--stats');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		@lines = test_pg_waldump($path, '--stats=record');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		@lines = test_pg_waldump($path, '--rmgr' => 'Btree');
 		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		@lines = test_pg_waldump($path, '--fork' => 'init');
 		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
 		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
 			0, 'only lines for selected relation');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
 			'--block' => 1);
 		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+
+		# Cleanup.
+		unlink $path if $scenario->{'is_archive'};
 	}
 }
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 57a8f0366a5..981cdb69175 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -139,6 +139,8 @@ ArchiveOpts
 ArchiveShutdownCB
 ArchiveStartupCB
 ArchiveStreamState
+ArchivedWALEntry
+ArchivedWAL_hash
 ArchiverOutput
 ArchiverStage
 ArrayAnalyzeExtraData
@@ -3466,6 +3468,7 @@ astreamer_recovery_injector
 astreamer_tar_archiver
 astreamer_tar_parser
 astreamer_verify
+astreamer_waldump
 astreamer_zstd_frame
 auth_password_hook_typ
 autovac_table
-- 
2.47.1

From 1a41393da777838efb3b095b8ab1cafd1fe92623 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 6 Nov 2025 13:48:33 +0530
Subject: [PATCH v8 5/8] pg_waldump: Remove the restriction on the order of
 archived WAL files.

With previous patch, pg_waldump would stop decoding if WAL files were
not in the required sequence. With this patch, decoding will now
continue.  Any WAL file that is out of order will be written to a
temporary location, from which it will be read later. Once a temporary
file has been read, it will be removed.
---
 src/bin/pg_waldump/archive_waldump.c | 220 +++++++++++++++++++++++++--
 src/bin/pg_waldump/pg_waldump.c      |  41 ++++-
 src/bin/pg_waldump/pg_waldump.h      |   4 +
 src/bin/pg_waldump/t/001_basic.pl    |   3 +-
 4 files changed, 256 insertions(+), 12 deletions(-)

diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
index f991633e58c..d38855e9a10 100644
--- a/src/bin/pg_waldump/archive_waldump.c
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -17,6 +17,7 @@
 #include <unistd.h>
 
 #include "access/xlog_internal.h"
+#include "common/file_perm.h"
 #include "common/hashfn.h"
 #include "common/logging.h"
 #include "fe_utils/simple_list.h"
@@ -27,6 +28,9 @@
  */
 #define READ_CHUNK_SIZE				(128 * 1024)
 
+/* Temporary exported WAL file directory */
+static char *TmpWalSegDir = NULL;
+
 /* Structure for storing the WAL segment data from the archive */
 typedef struct ArchivedWALEntry
 {
@@ -65,6 +69,11 @@ typedef struct astreamer_waldump
 static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
 static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
 											   XLogDumpPrivate *privateInfo);
+static void setup_tmpseg_dir(const char *waldir);
+static void cleanup_tmpseg_dir_atexit(void);
+
+static FILE *prepare_tmp_write(XLogSegNo segno);
+static void perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file);
 
 static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
 static void astreamer_waldump_content(astreamer *streamer,
@@ -120,10 +129,11 @@ is_archive_file(const char *fname, pg_compress_algorithm *compression)
 }
 
 /*
- * Initializes the tar archive reader to read WAL files from the archive,
- * creates a hash table to store them, performs quick existence checks for WAL
- * entries in the archive and retrieves the WAL segment size, and sets up
- * filtering criteria for relevant entries.
+ * Initializes the tar archive reader, creates a hash table for WAL entries,
+ * checks for existing valid WAL segments in the archive file and retrieves the
+ * segment size, and sets up filters for relevant entries. It also configures a
+ * temporary directory for out-of-order WAL data and registers an exit callback
+ * to clean up temporary files.
  */
 void
 init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
@@ -199,6 +209,13 @@ init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
 		privateInfo->endSegNo = UINT64_MAX;
 	else
 		XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+
+	/*
+	 * Setup temporary directory to store WAL segments and set up an exit
+	 * callback to remove it upon completion.
+	 */
+	setup_tmpseg_dir(waldir);
+	atexit(cleanup_tmpseg_dir_atexit);
 }
 
 /*
@@ -374,13 +391,16 @@ read_archive_file(XLogDumpPrivate *privateInfo, Size count)
 /*
  * Returns the archived WAL entry from the hash table if it exists. Otherwise,
  * it invokes the routine to read the archived file and retrieve the entry if
- * it is not already in hash table.
+ * it is not already present in the hash table. If the archive streamer happens
+ * to be reading a WAL from archive file that is not currently needed, that WAL
+ * data is written to a temporary file.
  */
 static ArchivedWALEntry *
 get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 {
 	ArchivedWALEntry *entry = NULL;
 	char		fname[MAXFNAMELEN];
+	FILE	   *write_fp = NULL;
 
 	/* Search hash table */
 	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
@@ -423,11 +443,32 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 			continue;
 		}
 
-		/* WAL segments must be archived in order */
-		pg_log_error("WAL files are not archived in sequential order");
-		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
-							segno, entry->segno);
-		exit(1);
+		/*
+		 * Archive streamer is currently reading a file that isn't the one
+		 * asked for, but it's required for a future feature. It should be
+		 * written to a temporary location for retrieval when needed.
+		 */
+
+		/* Create a temporary file if one does not already exist */
+		if (!entry->tmpseg_exists)
+		{
+			write_fp = prepare_tmp_write(entry->segno);
+			entry->tmpseg_exists = true;
+		}
+
+		/* Flush data from the buffer to the file */
+		perform_tmp_write(entry->segno, &entry->buf, write_fp);
+		resetStringInfo(&entry->buf);
+
+		/*
+		 * The change in the current segment entry indicates that the reading
+		 * of this file has ended.
+		 */
+		if (entry != privateInfo->cur_wal && write_fp != NULL)
+		{
+			fclose(write_fp);
+			write_fp = NULL;
+		}
 	}
 
 	/* Requested WAL segment not found */
@@ -435,6 +476,165 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 	pg_fatal("could not find file \"%s\" in archive", fname);
 }
 
+/*
+ * Set up a temporary directory to temporarily store WAL segments.
+ */
+static void
+setup_tmpseg_dir(const char *waldir)
+{
+	char	   *template;
+
+	/*
+	 * Use the directory specified by the TEMDIR environment variable. If it's
+	 * not set, use the provided WAL directory to extract WAL file
+	 * temporarily.
+	 */
+	template = psprintf("%s/waldump_tmp-XXXXXX",
+						getenv("TMPDIR") ? getenv("TMPDIR") : waldir);
+	TmpWalSegDir = mkdtemp(template);
+
+	if (TmpWalSegDir == NULL)
+		pg_fatal("could not create directory \"%s\": %m", template);
+
+	canonicalize_path(TmpWalSegDir);
+
+	pg_log_debug("created directory \"%s\"", TmpWalSegDir);
+}
+
+/*
+ * Removes the temporarily store WAL segments, if any, at exiting.
+ */
+static void
+cleanup_tmpseg_dir_atexit(void)
+{
+	ArchivedWAL_iterator it;
+	ArchivedWALEntry *entry;
+
+	/* Remove temporary segments */
+	ArchivedWAL_start_iterate(ArchivedWAL_HTAB, &it);
+	while ((entry = ArchivedWAL_iterate(ArchivedWAL_HTAB, &it)) != NULL)
+	{
+		if (entry->tmpseg_exists)
+		{
+			remove_tmp_walseg(entry->segno, false);
+			entry->tmpseg_exists = false;
+		}
+	}
+
+	/* Remove temporary directory */
+	if (rmdir(TmpWalSegDir) == 0)
+		pg_log_debug("removed directory \"%s\"", TmpWalSegDir);
+}
+
+/*
+ * Generate the temporary WAL file path.
+ *
+ * Note that the caller is responsible to pfree it.
+ */
+char *
+get_tmp_walseg_path(XLogSegNo segno)
+{
+	char	   *fpath = (char *) palloc(MAXPGPATH);
+
+	Assert(TmpWalSegDir);
+
+	snprintf(fpath, MAXPGPATH, "%s/%08X%08X",
+			 TmpWalSegDir,
+			 (uint32) (segno / XLogSegmentsPerXLogId(WalSegSz)),
+			 (uint32) (segno % XLogSegmentsPerXLogId(WalSegSz)));
+
+	return fpath;
+}
+
+/*
+ * Routine to check whether a temporary file exists for the corresponding WAL
+ * segment number.
+ */
+bool
+tmp_walseg_exists(XLogSegNo segno)
+{
+	ArchivedWALEntry *entry;
+
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry == NULL)
+		return false;
+
+	return entry->tmpseg_exists;
+}
+
+/*
+ * Create an empty placeholder file and return its handle.
+ */
+static FILE *
+prepare_tmp_write(XLogSegNo segno)
+{
+	FILE	   *file;
+	char	   *fpath;
+
+	fpath = get_tmp_walseg_path(segno);
+
+	/* Create an empty placeholder */
+	file = fopen(fpath, PG_BINARY_W);
+	if (file == NULL)
+		pg_fatal("could not create file \"%s\": %m", fpath);
+
+#ifndef WIN32
+	if (chmod(fpath, pg_file_create_mode))
+		pg_fatal("could not set permissions on file \"%s\": %m",
+				 fpath);
+#endif
+
+	pg_log_debug("temporarily exporting file \"%s\"", fpath);
+	pfree(fpath);
+
+	return file;
+}
+
+/*
+ * Write buffer data to the given file handle.
+ */
+static void
+perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file)
+{
+	Assert(file);
+
+	errno = 0;
+	if (buf->len > 0 && fwrite(buf->data, buf->len, 1, file) != 1)
+	{
+		/*
+		 * If write didn't set errno, assume problem is no disk space
+		 */
+		if (errno == 0)
+			errno = ENOSPC;
+		pg_fatal("could not write to file \"%s\": %m",
+				 get_tmp_walseg_path(segno));
+	}
+}
+
+/*
+ * Remove temporary file
+ */
+void
+remove_tmp_walseg(XLogSegNo segno, bool update_entry)
+{
+	char	   *fpath = get_tmp_walseg_path(segno);
+
+	if (unlink(fpath) == 0)
+		pg_log_debug("removed file \"%s\"", fpath);
+	pfree(fpath);
+
+	/* Update entry if requested */
+	if (update_entry)
+	{
+		ArchivedWALEntry *entry;
+
+		entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+		Assert(entry != NULL);
+		entry->tmpseg_exists = false;
+	}
+}
+
 /*
  * Create an astreamer that can read WAL from tar file.
  */
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 02ad141e44a..4c5974a6ae1 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -466,11 +466,50 @@ TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 {
 	XLogDumpPrivate *private = state->private_data;
 	int			count = required_read_len(private, targetPagePtr, reqLen);
+	XLogSegNo	nextSegNo;
 
 	if (private->endptr_reached)
 		return -1;
 
-	/* Read the WAL page from the archive streamer */
+	/*
+	 * If the target page is in a different segment, first check for the WAL
+	 * segment's physical existence in the temporary directory.
+	 */
+	nextSegNo = state->seg.ws_segno;
+	if (!XLByteInSeg(targetPagePtr, nextSegNo, WalSegSz))
+	{
+		if (state->seg.ws_file >= 0)
+		{
+			close(state->seg.ws_file);
+			state->seg.ws_file = -1;
+
+			/* Remove this file, as it is no longer needed. */
+			remove_tmp_walseg(nextSegNo, true);
+		}
+
+		XLByteToSeg(targetPagePtr, nextSegNo, WalSegSz);
+		state->seg.ws_tli = private->timeline;
+		state->seg.ws_segno = nextSegNo;
+
+		/*
+		 * If the next segment exists, open it and continue reading from there
+		 */
+		if (tmp_walseg_exists(nextSegNo))
+		{
+			char	   *fpath;
+
+			fpath = get_tmp_walseg_path(nextSegNo);
+			state->seg.ws_file = open(fpath, O_RDONLY | PG_BINARY, 0);
+			pfree(fpath);
+		}
+	}
+
+	/* Continue reading from the open WAL segment, if any */
+	if (state->seg.ws_file >= 0)
+		return WALDumpReadPage(state, targetPagePtr, count, targetPtr,
+							   readBuff);
+
+	/* Otherwise, read the WAL page from the archive streamer */
 	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
 }
 
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 54758c3548a..5c1fb1e080a 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -58,4 +58,8 @@ extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
 								  XLogRecPtr targetPagePtr,
 								  Size count, char *readBuff);
 
+extern char *get_tmp_walseg_path(XLogSegNo segno);
+extern bool tmp_walseg_exists(XLogSegNo segno);
+extern void remove_tmp_walseg(XLogSegNo segno, bool update_entry);
+
 #endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 443126a9ce6..d5fa1f6d28d 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -7,6 +7,7 @@ use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
+use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
 
@@ -272,7 +273,7 @@ sub generate_archive
 	}
 	closedir $dh;
 
-	@files = sort @files;
+	@files = shuffle @files;
 
 	# move into the WAL directory before archiving files
 	my $cwd = getcwd;
-- 
2.47.1

From 5cc37e03ae3b6cf3d01b681bafdc0cc3cf136c27 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 14:47:43 +0530
Subject: [PATCH v8 6/8] pg_verifybackup: Delay default WAL directory
 preparation.

We are not sure whether to parse WAL from a directory or an archive
until the backup format is known. Therefore, we delay preparing the
default WAL directory until the point of parsing. This delay is
harmless, as the WAL directory is not used elsewhere.
---
 src/bin/pg_verifybackup/pg_verifybackup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 8d5befa947f..a502e795b2e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -285,10 +285,6 @@ main(int argc, char **argv)
 		manifest_path = psprintf("%s/backup_manifest",
 								 context.backup_directory);
 
-	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
-
 	/*
 	 * Try to read the manifest. We treat any errors encountered while parsing
 	 * the manifest as fatal; there doesn't seem to be much point in trying to
@@ -368,6 +364,10 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
+	/* By default, look for the WAL in the backup directory, too. */
+	if (wal_directory == NULL)
+		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
-- 
2.47.1

From cfb5b951450b65f32b7a2357630c184af36bdba7 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 24 Jul 2025 16:37:43 +0530
Subject: [PATCH v8 7/8] pg_verifybackup: Rename the wal-directory switch to
 wal-path

With previous patches to pg_waldump can now decode WAL directly from
tar files.  This means you'll be able to specify a tar archive path
instead of a traditional WAL directory.

To keep things consistent and more versatile, we should also
generalize the input switch for pg_verifybackup. It should accept
either a directory or a tar file path that contains WALs. This change
will also aligning it with the existing manifest-path switch naming.
---
 doc/src/sgml/ref/pg_verifybackup.sgml     |  2 +-
 src/bin/pg_verifybackup/pg_verifybackup.c | 22 +++++++++++-----------
 src/bin/pg_verifybackup/po/de.po          |  4 ++--
 src/bin/pg_verifybackup/po/el.po          |  4 ++--
 src/bin/pg_verifybackup/po/es.po          |  4 ++--
 src/bin/pg_verifybackup/po/fr.po          |  4 ++--
 src/bin/pg_verifybackup/po/it.po          |  4 ++--
 src/bin/pg_verifybackup/po/ja.po          |  4 ++--
 src/bin/pg_verifybackup/po/ka.po          |  4 ++--
 src/bin/pg_verifybackup/po/ko.po          |  4 ++--
 src/bin/pg_verifybackup/po/ru.po          |  4 ++--
 src/bin/pg_verifybackup/po/sv.po          |  4 ++--
 src/bin/pg_verifybackup/po/uk.po          |  4 ++--
 src/bin/pg_verifybackup/po/zh_CN.po       |  4 ++--
 src/bin/pg_verifybackup/po/zh_TW.po       |  4 ++--
 src/bin/pg_verifybackup/t/007_wal.pl      |  4 ++--
 16 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index 61c12975e4a..e9b8bfd51b1 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -261,7 +261,7 @@ PostgreSQL documentation
 
      <varlistentry>
       <term><option>-w <replaceable class="parameter">path</replaceable></option></term>
-      <term><option>--wal-directory=<replaceable class="parameter">path</replaceable></option></term>
+      <term><option>--wal-path=<replaceable class="parameter">path</replaceable></option></term>
       <listitem>
        <para>
         Try to parse WAL files stored in the specified directory, rather than
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index a502e795b2e..9fcd6be004e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -93,7 +93,7 @@ static void verify_file_checksum(verifier_context *context,
 								 uint8 *buffer);
 static void parse_required_wal(verifier_context *context,
 							   char *pg_waldump_path,
-							   char *wal_directory);
+							   char *wal_path);
 static astreamer *create_archive_verifier(verifier_context *context,
 										  char *archive_name,
 										  Oid tblspc_oid,
@@ -126,7 +126,7 @@ main(int argc, char **argv)
 		{"progress", no_argument, NULL, 'P'},
 		{"quiet", no_argument, NULL, 'q'},
 		{"skip-checksums", no_argument, NULL, 's'},
-		{"wal-directory", required_argument, NULL, 'w'},
+		{"wal-path", required_argument, NULL, 'w'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -135,7 +135,7 @@ main(int argc, char **argv)
 	char	   *manifest_path = NULL;
 	bool		no_parse_wal = false;
 	bool		quiet = false;
-	char	   *wal_directory = NULL;
+	char	   *wal_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -221,8 +221,8 @@ main(int argc, char **argv)
 				context.skip_checksums = true;
 				break;
 			case 'w':
-				wal_directory = pstrdup(optarg);
-				canonicalize_path(wal_directory);
+				wal_path = pstrdup(optarg);
+				canonicalize_path(wal_path);
 				break;
 			default:
 				/* getopt_long already emitted a complaint */
@@ -365,15 +365,15 @@ main(int argc, char **argv)
 		verify_backup_checksums(&context);
 
 	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+	if (wal_path == NULL)
+		wal_path = psprintf("%s/pg_wal", context.backup_directory);
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
 	 */
 	if (!no_parse_wal)
-		parse_required_wal(&context, pg_waldump_path, wal_directory);
+		parse_required_wal(&context, pg_waldump_path, wal_path);
 
 	/*
 	 * If everything looks OK, tell the user this, unless we were asked to
@@ -1198,7 +1198,7 @@ verify_file_checksum(verifier_context *context, manifest_file *m,
  */
 static void
 parse_required_wal(verifier_context *context, char *pg_waldump_path,
-				   char *wal_directory)
+				   char *wal_path)
 {
 	manifest_data *manifest = context->manifest;
 	manifest_wal_range *this_wal_range = manifest->first_wal_range;
@@ -1208,7 +1208,7 @@ parse_required_wal(verifier_context *context, char *pg_waldump_path,
 		char	   *pg_waldump_cmd;
 
 		pg_waldump_cmd = psprintf("\"%s\" --quiet --path=\"%s\" --timeline=%u --start=%X/%08X --end=%X/%08X\n",
-								  pg_waldump_path, wal_directory, this_wal_range->tli,
+								  pg_waldump_path, wal_path, this_wal_range->tli,
 								  LSN_FORMAT_ARGS(this_wal_range->start_lsn),
 								  LSN_FORMAT_ARGS(this_wal_range->end_lsn));
 		fflush(NULL);
@@ -1376,7 +1376,7 @@ usage(void)
 	printf(_("  -P, --progress              show progress information\n"));
 	printf(_("  -q, --quiet                 do not print any output, except for errors\n"));
 	printf(_("  -s, --skip-checksums        skip checksum verification\n"));
-	printf(_("  -w, --wal-directory=PATH    use specified path for WAL files\n"));
+	printf(_("  -w, --wal-path=PATH         use specified path for WAL files\n"));
 	printf(_("  -V, --version               output version information, then exit\n"));
 	printf(_("  -?, --help                  show this help, then exit\n"));
 	printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
diff --git a/src/bin/pg_verifybackup/po/de.po b/src/bin/pg_verifybackup/po/de.po
index a9e24931100..9b5cd5898cf 100644
--- a/src/bin/pg_verifybackup/po/de.po
+++ b/src/bin/pg_verifybackup/po/de.po
@@ -785,8 +785,8 @@ msgstr "  -s, --skip-checksums        Überprüfung der Prüfsummen überspringe
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PFAD    angegebenen Pfad für WAL-Dateien verwenden\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/el.po b/src/bin/pg_verifybackup/po/el.po
index 3e3f20c67c5..81442f51c17 100644
--- a/src/bin/pg_verifybackup/po/el.po
+++ b/src/bin/pg_verifybackup/po/el.po
@@ -494,8 +494,8 @@ msgstr "  -s, --skip-checksums        παράκαμψε την επαλήθευ
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    χρησιμοποίησε την καθορισμένη διαδρομή για αρχεία WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/es.po b/src/bin/pg_verifybackup/po/es.po
index 0cb958f3448..7f729fa35ba 100644
--- a/src/bin/pg_verifybackup/po/es.po
+++ b/src/bin/pg_verifybackup/po/es.po
@@ -495,8 +495,8 @@ msgstr "  -s, --skip-checksums        omitir la verificación de la suma de comp
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    utilizar la ruta especificada para los archivos WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    utilizar la ruta especificada para los archivos WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/fr.po b/src/bin/pg_verifybackup/po/fr.po
index da8c72f6427..09937966fa7 100644
--- a/src/bin/pg_verifybackup/po/fr.po
+++ b/src/bin/pg_verifybackup/po/fr.po
@@ -498,8 +498,8 @@ msgstr "  -s, --skip-checksums        ignore la vérification des sommes de cont
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=CHEMIN  utilise le chemin spécifié pour les fichiers WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/it.po b/src/bin/pg_verifybackup/po/it.po
index 317b0b71e7f..4da68d0074e 100644
--- a/src/bin/pg_verifybackup/po/it.po
+++ b/src/bin/pg_verifybackup/po/it.po
@@ -472,8 +472,8 @@ msgstr "  -s, --skip-checksums         salta la verifica del checksum\n"
 
 #: pg_verifybackup.c:911
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH     usa il percorso specificato per i file WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH     usa il percorso specificato per i file WAL\n"
 
 #: pg_verifybackup.c:912
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ja.po b/src/bin/pg_verifybackup/po/ja.po
index c910fb236cc..a948959b54f 100644
--- a/src/bin/pg_verifybackup/po/ja.po
+++ b/src/bin/pg_verifybackup/po/ja.po
@@ -672,8 +672,8 @@ msgstr "  -s, --skip-checksums        チェックサム検証をスキップ\n"
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    WALファイルに指定したパスを使用する\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    WALファイルに指定したパスを使用する\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ka.po b/src/bin/pg_verifybackup/po/ka.po
index 982751984c7..ef2799316a8 100644
--- a/src/bin/pg_verifybackup/po/ka.po
+++ b/src/bin/pg_verifybackup/po/ka.po
@@ -784,8 +784,8 @@ msgstr "  -s, --skip-checksums        საკონტროლო ჯამ
 
 #: pg_verifybackup.c:1379
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=ბილიკი    WAL ფაილებისთვის მითითებული ბილიკის გამოყენება\n"
 
 #: pg_verifybackup.c:1380
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ko.po b/src/bin/pg_verifybackup/po/ko.po
index acdc3da5e02..eaf91ef1e98 100644
--- a/src/bin/pg_verifybackup/po/ko.po
+++ b/src/bin/pg_verifybackup/po/ko.po
@@ -501,8 +501,8 @@ msgstr "  -s, --skip-checksums        체크섬 검사 건너뜀\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=경로    WAL 파일이 있는 경로 지정\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=경로    WAL 파일이 있는 경로 지정\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/ru.po b/src/bin/pg_verifybackup/po/ru.po
index 64005feedfd..7fb0e5ab1f6 100644
--- a/src/bin/pg_verifybackup/po/ru.po
+++ b/src/bin/pg_verifybackup/po/ru.po
@@ -507,9 +507,9 @@ msgstr "  -s, --skip-checksums        пропустить проверку ко
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
 msgstr ""
-"  -w, --wal-directory=ПУТЬ    использовать заданный путь к файлам WAL\n"
+"  -w, --wal-path=ПУТЬ    использовать заданный путь к файлам WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/sv.po b/src/bin/pg_verifybackup/po/sv.po
index 17240feeb5c..97125838e8c 100644
--- a/src/bin/pg_verifybackup/po/sv.po
+++ b/src/bin/pg_verifybackup/po/sv.po
@@ -492,8 +492,8 @@ msgstr "  -s, --skip-checksums        hoppa över verifiering av kontrollsummor\
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=SÖKVÄG  använd denna sökväg till WAL-filer\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=SÖKVÄG  använd denna sökväg till WAL-filer\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/uk.po b/src/bin/pg_verifybackup/po/uk.po
index 034b9764232..63f8041ab38 100644
--- a/src/bin/pg_verifybackup/po/uk.po
+++ b/src/bin/pg_verifybackup/po/uk.po
@@ -484,8 +484,8 @@ msgstr "  -s, --skip-checksums не перевіряти контрольні с
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH використовувати вказаний шлях для файлів WAL\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH використовувати вказаний шлях для файлів WAL\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_CN.po b/src/bin/pg_verifybackup/po/zh_CN.po
index b7d97c8976d..fb6fcae8b82 100644
--- a/src/bin/pg_verifybackup/po/zh_CN.po
+++ b/src/bin/pg_verifybackup/po/zh_CN.po
@@ -465,8 +465,8 @@ msgstr "  -s, --skip-checksums        跳过校验和验证\n"
 
 #: pg_verifybackup.c:919
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    对WAL文件使用指定路径\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    对WAL文件使用指定路径\n"
 
 #: pg_verifybackup.c:920
 #, c-format
diff --git a/src/bin/pg_verifybackup/po/zh_TW.po b/src/bin/pg_verifybackup/po/zh_TW.po
index c1b710b0a36..568f972b0bb 100644
--- a/src/bin/pg_verifybackup/po/zh_TW.po
+++ b/src/bin/pg_verifybackup/po/zh_TW.po
@@ -555,8 +555,8 @@ msgstr "  -s, --skip-checksums        跳過檢查碼驗證\n"
 
 #: pg_verifybackup.c:992
 #, c-format
-msgid "  -w, --wal-directory=PATH    use specified path for WAL files\n"
-msgstr "  -w, --wal-directory=PATH    用指定的路徑存放 WAL 檔\n"
+msgid "  -w, --wal-path=PATH    use specified path for WAL files\n"
+msgstr "  -w, --wal-path=PATH    用指定的路徑存放 WAL 檔\n"
 
 #: pg_verifybackup.c:993
 #, c-format
diff --git a/src/bin/pg_verifybackup/t/007_wal.pl b/src/bin/pg_verifybackup/t/007_wal.pl
index babc4f0a86b..b07f80719b0 100644
--- a/src/bin/pg_verifybackup/t/007_wal.pl
+++ b/src/bin/pg_verifybackup/t/007_wal.pl
@@ -42,10 +42,10 @@ command_ok([ 'pg_verifybackup', '--no-parse-wal', $backup_path ],
 command_ok(
 	[
 		'pg_verifybackup',
-		'--wal-directory' => $relocated_pg_wal,
+		'--wal-path' => $relocated_pg_wal,
 		$backup_path
 	],
-	'--wal-directory can be used to specify WAL directory');
+	'--wal-path can be used to specify WAL directory');
 
 # Move directory back to original location.
 rename($relocated_pg_wal, $original_pg_wal) || die "rename pg_wal back: $!";
-- 
2.47.1

From d0028b96f02c6f15231f4788b88abd9ff46b17f1 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 17 Jul 2025 16:39:36 +0530
Subject: [PATCH v8 8/8] pg_verifybackup: enabled WAL parsing for tar-format
 backup

Now that pg_waldump supports decoding from tar archives, we should
leverage this functionality to remove the previous restriction on WAL
parsing for tar-backed formats.
---
 doc/src/sgml/ref/pg_verifybackup.sgml         |  5 +-
 src/bin/pg_verifybackup/pg_verifybackup.c     | 66 +++++++++++++------
 src/bin/pg_verifybackup/t/002_algorithm.pl    |  4 --
 src/bin/pg_verifybackup/t/003_corruption.pl   |  4 +-
 src/bin/pg_verifybackup/t/008_untar.pl        |  5 +-
 src/bin/pg_verifybackup/t/010_client_untar.pl |  5 +-
 6 files changed, 50 insertions(+), 39 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index e9b8bfd51b1..16b50b5a4df 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -36,10 +36,7 @@ PostgreSQL documentation
    <literal>backup_manifest</literal> generated by the server at the time
    of the backup. The backup may be stored either in the "plain" or the "tar"
    format; this includes tar-format backups compressed with any algorithm
-   supported by <application>pg_basebackup</application>. However, at present,
-   <literal>WAL</literal> verification is supported only for plain-format
-   backups. Therefore, if the backup is stored in tar-format, the
-   <literal>-n, --no-parse-wal</literal> option should be used.
+   supported by <application>pg_basebackup</application>.
   </para>
 
   <para>
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 9fcd6be004e..6915fc7f28e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -74,7 +74,9 @@ pg_noreturn static void report_manifest_error(JsonManifestParseContext *context,
 											  const char *fmt,...)
 			pg_attribute_printf(2, 3);
 
-static void verify_tar_backup(verifier_context *context, DIR *dir);
+static void verify_tar_backup(verifier_context *context, DIR *dir,
+							  char **base_archive_path,
+							  char **wal_archive_path);
 static void verify_plain_backup_directory(verifier_context *context,
 										  char *relpath, char *fullpath,
 										  DIR *dir);
@@ -83,7 +85,9 @@ static void verify_plain_backup_file(verifier_context *context, char *relpath,
 static void verify_control_file(const char *controlpath,
 								uint64 manifest_system_identifier);
 static void precheck_tar_backup_file(verifier_context *context, char *relpath,
-									 char *fullpath, SimplePtrList *tarfiles);
+									 char *fullpath, SimplePtrList *tarfiles,
+									 char **base_archive_path,
+									 char **wal_archive_path);
 static void verify_tar_file(verifier_context *context, char *relpath,
 							char *fullpath, astreamer *streamer);
 static void report_extra_backup_files(verifier_context *context);
@@ -136,6 +140,8 @@ main(int argc, char **argv)
 	bool		no_parse_wal = false;
 	bool		quiet = false;
 	char	   *wal_path = NULL;
+	char	   *base_archive_path = NULL;
+	char	   *wal_archive_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -327,17 +333,6 @@ main(int argc, char **argv)
 		pfree(path);
 	}
 
-	/*
-	 * XXX: In the future, we should consider enhancing pg_waldump to read WAL
-	 * files from an archive.
-	 */
-	if (!no_parse_wal && context.format == 't')
-	{
-		pg_log_error("pg_waldump cannot read tar files");
-		pg_log_error_hint("You must use -n/--no-parse-wal when verifying a tar-format backup.");
-		exit(1);
-	}
-
 	/*
 	 * Perform the appropriate type of verification appropriate based on the
 	 * backup format. This will close 'dir'.
@@ -346,7 +341,7 @@ main(int argc, char **argv)
 		verify_plain_backup_directory(&context, NULL, context.backup_directory,
 									  dir);
 	else
-		verify_tar_backup(&context, dir);
+		verify_tar_backup(&context, dir, &base_archive_path, &wal_archive_path);
 
 	/*
 	 * The "matched" flag should now be set on every entry in the hash table.
@@ -364,9 +359,28 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
-	/* By default, look for the WAL in the backup directory, too. */
+	/*
+	 * By default, WAL files are expected to be found in the backup directory
+	 * for plain-format backups. In the case of tar-format backups, if a
+	 * separate WAL archive is not found, the WAL files are most likely
+	 * included within the main data directory archive.
+	 */
 	if (wal_path == NULL)
-		wal_path = psprintf("%s/pg_wal", context.backup_directory);
+	{
+		if (context.format == 'p')
+			wal_path = psprintf("%s/pg_wal", context.backup_directory);
+		else if (wal_archive_path)
+			wal_path = wal_archive_path;
+		else if (base_archive_path)
+			wal_path = base_archive_path;
+		else
+		{
+			pg_log_error("wal archive not found");
+			pg_log_error_hint("Specify the correct path using the option -w/--wal-path."
+							  "Or you must use -n/--no-parse-wal when verifying a tar-format backup.");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
@@ -787,7 +801,8 @@ verify_control_file(const char *controlpath, uint64 manifest_system_identifier)
  * close when we're done with it.
  */
 static void
-verify_tar_backup(verifier_context *context, DIR *dir)
+verify_tar_backup(verifier_context *context, DIR *dir, char **base_archive_path,
+				  char **wal_archive_path)
 {
 	struct dirent *dirent;
 	SimplePtrList tarfiles = {NULL, NULL};
@@ -816,7 +831,8 @@ verify_tar_backup(verifier_context *context, DIR *dir)
 			char	   *fullpath;
 
 			fullpath = psprintf("%s/%s", context->backup_directory, filename);
-			precheck_tar_backup_file(context, filename, fullpath, &tarfiles);
+			precheck_tar_backup_file(context, filename, fullpath, &tarfiles,
+									 base_archive_path, wal_archive_path);
 			pfree(fullpath);
 		}
 	}
@@ -875,11 +891,13 @@ verify_tar_backup(verifier_context *context, DIR *dir)
  *
  * The arguments to this function are mostly the same as the
  * verify_plain_backup_file. The additional argument outputs a list of valid
- * tar files.
+ * tar files, along with the full paths to the main archive and the WAL
+ * directory archive.
  */
 static void
 precheck_tar_backup_file(verifier_context *context, char *relpath,
-						 char *fullpath, SimplePtrList *tarfiles)
+						 char *fullpath, SimplePtrList *tarfiles,
+						 char **base_archive_path, char **wal_archive_path)
 {
 	struct stat sb;
 	Oid			tblspc_oid = InvalidOid;
@@ -918,9 +936,17 @@ precheck_tar_backup_file(verifier_context *context, char *relpath,
 	 * extension such as .gz, .lz4, or .zst.
 	 */
 	if (strncmp("base", relpath, 4) == 0)
+	{
 		suffix = relpath + 4;
+
+		*base_archive_path = pstrdup(fullpath);
+	}
 	else if (strncmp("pg_wal", relpath, 6) == 0)
+	{
 		suffix = relpath + 6;
+
+		*wal_archive_path = pstrdup(fullpath);
+	}
 	else
 	{
 		/* Expected a <tablespaceoid>.tar file here. */
diff --git a/src/bin/pg_verifybackup/t/002_algorithm.pl b/src/bin/pg_verifybackup/t/002_algorithm.pl
index ae16c11bc4d..4f284a9e828 100644
--- a/src/bin/pg_verifybackup/t/002_algorithm.pl
+++ b/src/bin/pg_verifybackup/t/002_algorithm.pl
@@ -30,10 +30,6 @@ sub test_checksums
 	{
 		# Add switch to get a tar-format backup
 		push @backup, ('--format' => 'tar');
-
-		# Add switch to skip WAL verification, which is not yet supported for
-		# tar-format backups
-		push @verify, ('--no-parse-wal');
 	}
 
 	# A backup with a bogus algorithm should fail.
diff --git a/src/bin/pg_verifybackup/t/003_corruption.pl b/src/bin/pg_verifybackup/t/003_corruption.pl
index 1dd60f709cf..f1ebdbb46b4 100644
--- a/src/bin/pg_verifybackup/t/003_corruption.pl
+++ b/src/bin/pg_verifybackup/t/003_corruption.pl
@@ -193,10 +193,8 @@ for my $scenario (@scenario)
 			command_ok([ $tar, '-cf' => "$tar_backup_path/base.tar", '.' ]);
 			chdir($cwd) || die "chdir: $!";
 
-			# Now check that the backup no longer verifies. We must use -n
-			# here, because pg_waldump can't yet read WAL from a tarfile.
 			command_fails_like(
-				[ 'pg_verifybackup', '--no-parse-wal', $tar_backup_path ],
+				[ 'pg_verifybackup', $tar_backup_path ],
 				$scenario->{'fails_like'},
 				"corrupt backup fails verification: $name");
 
diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index bc3d6b352ad..09079a94fee 100644
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -47,7 +47,6 @@ my $tsoid = $primary->safe_psql(
 		SELECT oid FROM pg_tablespace WHERE spcname = 'regress_ts1'));
 
 my $backup_path = $primary->backup_dir . '/server-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -123,14 +122,12 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
 		rmtree($backup_path);
-		rmtree($extract_path);
 	}
 }
 
diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index b62faeb5acf..5b0e76ee69d 100644
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -32,7 +32,6 @@ print $jf $junk_data;
 close $jf;
 
 my $backup_path = $primary->backup_dir . '/client-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -137,13 +136,11 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
-		rmtree($extract_path);
 		rmtree($backup_path);
 	}
 }
-- 
2.47.1

From 38322b7e5062f7c45f47e09655a1c964e9eeb68b Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 24 Jun 2025 11:33:20 +0530
Subject: [PATCH v9 1/8] Refactor: pg_waldump: Move some declarations to new
 pg_waldump.h

This change prepares for a second source file in this directory to
support reading WAL from tar files. Common structures, declarations,
and functions are being exported through this include file so
they can be used in both files.
---
 src/bin/pg_waldump/pg_waldump.c | 12 +++---------
 src/bin/pg_waldump/pg_waldump.h | 27 +++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 9 deletions(-)
 create mode 100644 src/bin/pg_waldump/pg_waldump.h

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index c6d6ba79e44..6680280dbbc 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -29,6 +29,7 @@
 #include "common/logging.h"
 #include "common/relpath.h"
 #include "getopt_long.h"
+#include "pg_waldump.h"
 #include "rmgrdesc.h"
 #include "storage/bufpage.h"
 
@@ -37,21 +38,14 @@
  * give a thought about doing the same in pg_walinspect contrib module as well.
  */
 
+int			WalSegSz;
+
 static const char *progname;
 
-static int	WalSegSz;
 static volatile sig_atomic_t time_to_stop = false;
 
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
-typedef struct XLogDumpPrivate
-{
-	TimeLineID	timeline;
-	XLogRecPtr	startptr;
-	XLogRecPtr	endptr;
-	bool		endptr_reached;
-} XLogDumpPrivate;
-
 typedef struct XLogDumpConfig
 {
 	/* display options */
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
new file mode 100644
index 00000000000..926d529f9d6
--- /dev/null
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -0,0 +1,27 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_waldump.h - decode and display WAL
+ *
+ * Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  src/bin/pg_waldump/pg_waldump.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_WALDUMP_H
+#define PG_WALDUMP_H
+
+#include "access/xlogdefs.h"
+
+extern int	WalSegSz;
+
+/* Contains the necessary information to drive WAL decoding */
+typedef struct XLogDumpPrivate
+{
+	TimeLineID	timeline;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
+	bool		endptr_reached;
+} XLogDumpPrivate;
+
+#endif							/* end of PG_WALDUMP_H */
-- 
2.47.1

From 01d144fe8af4d4232b4b043c2ef11b07d785b4bd Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 26 Jun 2025 11:42:53 +0530
Subject: [PATCH v9 2/8] Refactor: pg_waldump: Separate logic used to calculate
 the required read size.

This refactoring prepares the codebase for an upcoming patch that will
support reading WAL from tar files. The logic for calculating the
required read size has been updated to handle both normal WAL files
and WAL files located inside a tar archive.
---
 src/bin/pg_waldump/pg_waldump.c | 46 +++++++++++++++++++++++----------
 1 file changed, 33 insertions(+), 13 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 6680280dbbc..2c11e0e5ca1 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -327,6 +327,35 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/*
+ * Returns the size in bytes of the data to be read. Returns -1 if the end
+ * point has already been reached.
+ */
+static inline int
+required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
+				  int reqLen)
+{
+	int			count = XLOG_BLCKSZ;
+
+	if (unlikely(private->endptr_reached))
+		return -1;
+
+	if (XLogRecPtrIsValid(private->endptr))
+	{
+		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
+			count = XLOG_BLCKSZ;
+		else if (targetPagePtr + reqLen <= private->endptr)
+			count = private->endptr - targetPagePtr;
+		else
+		{
+			private->endptr_reached = true;
+			return -1;
+		}
+	}
+
+	return count;
+}
+
 /* pg_waldump's XLogReaderRoutine->segment_open callback */
 static void
 WALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
@@ -384,21 +413,12 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = XLOG_BLCKSZ;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
-	if (XLogRecPtrIsValid(private->endptr))
-	{
-		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
-			count = XLOG_BLCKSZ;
-		else if (targetPagePtr + reqLen <= private->endptr)
-			count = private->endptr - targetPagePtr;
-		else
-		{
-			private->endptr_reached = true;
-			return -1;
-		}
-	}
+	/* Bail out if the count to be read is not valid */
+	if (count < 0)
+		return -1;
 
 	if (!WALRead(state, readBuff, targetPagePtr, count, private->timeline,
 				 &errinfo))
-- 
2.47.1

From 60b4c33b9b95c3d24a8200dae5cbc75bb09daef8 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 25 Nov 2025 16:12:11 +0530
Subject: [PATCH v9 3/8] Refactor: pg_waldump: Restructure TAP tests.

Restructured some tests to run inside a loop, facilitating their
re-execution for decoding WAL from tar archives.

== NOTE ==
  This is not intended to be committed separately. It can be merged
  with the next patch, which is the main patch implementing this
  feature.
---
 src/bin/pg_waldump/t/001_basic.pl | 123 ++++++++++++++++--------------
 1 file changed, 67 insertions(+), 56 deletions(-)

diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index f26d75e01cf..c8fdc7cb4f3 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -198,28 +198,6 @@ command_like(
 	],
 	qr/./,
 	'runs with start and end segment specified');
-command_fails_like(
-	[ 'pg_waldump', '--path' => $node->data_dir ],
-	qr/error: no start WAL location given/,
-	'path option requires start location');
-command_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-		'--end' => $end_lsn,
-	],
-	qr/./,
-	'runs with path option and start and end locations');
-command_fails_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-	],
-	qr/error: error in WAL record at/,
-	'falling off the end of the WAL results in an error');
-
 command_like(
 	[
 		'pg_waldump', '--quiet',
@@ -227,15 +205,6 @@ command_like(
 	],
 	qr/^$/,
 	'no output with --quiet option');
-command_fails_like(
-	[
-		'pg_waldump', '--quiet',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn
-	],
-	qr/error: error in WAL record at/,
-	'errors are shown with --quiet');
-
 
 # Test for: Display a message that we're skipping data if `from`
 # wasn't a pointer to the start of a record.
@@ -272,7 +241,6 @@ sub test_pg_waldump
 
 	my $result = IPC::Run::run [
 		'pg_waldump',
-		'--path' => $node->data_dir,
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
 		@opts
@@ -288,38 +256,81 @@ sub test_pg_waldump
 
 my @lines;
 
-@lines = test_pg_waldump;
-is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
+my @scenarios = (
+	{
+		'path' => $node->data_dir
+	});
 
-@lines = test_pg_waldump('--limit' => 6);
-is(@lines, 6, 'limit option observed');
+for my $scenario (@scenarios)
+{
+	my $path = $scenario->{'path'};
 
-@lines = test_pg_waldump('--fullpage');
-is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
+	SKIP:
+	{
+		command_fails_like(
+			[ 'pg_waldump', '--path' => $path ],
+			qr/error: no start WAL location given/,
+			'path option requires start location');
+		command_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+				'--end' => $end_lsn,
+			],
+			qr/./,
+			'runs with path option and start and end locations');
+		command_fails_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+			],
+			qr/error: error in WAL record at/,
+			'falling off the end of the WAL results in an error');
 
-@lines = test_pg_waldump('--stats');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		command_fails_like(
+			[
+				'pg_waldump', '--quiet',
+				'--path' => $path,
+				'--start' => $start_lsn
+			],
+			qr/error: error in WAL record at/,
+			'errors are shown with --quiet');
 
-@lines = test_pg_waldump('--stats=record');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		@lines = test_pg_waldump('--path' => $path);
+		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-@lines = test_pg_waldump('--rmgr' => 'Btree');
-is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		is(@lines, 6, 'limit option observed');
 
-@lines = test_pg_waldump('--fork' => 'init');
-is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
-is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
-	0, 'only lines for selected relation');
+		@lines = test_pg_waldump('--path' => $path, '--stats');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
-	'--block' => 1);
-is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
+		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+
+		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
+		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
+			0, 'only lines for selected relation');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
+			'--block' => 1);
+		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+	}
+}
 
 done_testing();
-- 
2.47.1

From bd2de61f136dd9111f69874af2782c4b2f6ab314 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 5 Nov 2025 15:40:36 +0530
Subject: [PATCH v9 4/8] pg_waldump: Add support for archived WAL decoding.

pg_waldump can now accept the path to a tar archive containing WAL
files and decode them. This feature was added primarily for
pg_verifybackup, which previously disabled WAL parsing for
tar-formatted backups.

Note that this patch requires that the WAL files within the archive be
in sequential order; an error will be reported otherwise. The next
patch is planned to remove this restriction.
---
 doc/src/sgml/ref/pg_waldump.sgml     |   8 +-
 src/bin/pg_waldump/Makefile          |   7 +-
 src/bin/pg_waldump/archive_waldump.c | 596 +++++++++++++++++++++++++++
 src/bin/pg_waldump/meson.build       |   4 +-
 src/bin/pg_waldump/pg_waldump.c      | 218 +++++++---
 src/bin/pg_waldump/pg_waldump.h      |  34 ++
 src/bin/pg_waldump/t/001_basic.pl    |  84 +++-
 src/tools/pgindent/typedefs.list     |   3 +
 8 files changed, 878 insertions(+), 76 deletions(-)
 create mode 100644 src/bin/pg_waldump/archive_waldump.c

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index ce23add5577..d004bb0f67e 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -141,13 +141,17 @@ PostgreSQL documentation
       <term><option>--path=<replaceable>path</replaceable></option></term>
       <listitem>
        <para>
-        Specifies a directory to search for WAL segment files or a
-        directory with a <literal>pg_wal</literal> subdirectory that
+        Specifies a tar archive or a directory to search for WAL segment files
+        or a directory with a <literal>pg_wal</literal> subdirectory that
         contains such files.  The default is to search in the current
         directory, the <literal>pg_wal</literal> subdirectory of the
         current directory, and the <literal>pg_wal</literal> subdirectory
         of <envar>PGDATA</envar>.
        </para>
+       <para>
+        If a tar archive is provided, its WAL segment files must be in
+        sequential order; otherwise, an error will be reported.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index 4c1ee649501..aabb87566a2 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -3,6 +3,9 @@
 PGFILEDESC = "pg_waldump - decode and display WAL"
 PGAPPICON=win32
 
+# make these available to TAP test scripts
+export TAR
+
 subdir = src/bin/pg_waldump
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
@@ -10,13 +13,15 @@ include $(top_builddir)/src/Makefile.global
 OBJS = \
 	$(RMGRDESCOBJS) \
 	$(WIN32RES) \
+	archive_waldump.o \
 	compat.o \
 	pg_waldump.o \
 	rmgrdesc.o \
 	xlogreader.o \
 	xlogstats.o
 
-override CPPFLAGS := -DFRONTEND $(CPPFLAGS)
+override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
new file mode 100644
index 00000000000..63141dc2ee2
--- /dev/null
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -0,0 +1,596 @@
+/*-------------------------------------------------------------------------
+ *
+ * archive_waldump.c
+ *		A generic facility for reading WAL data from tar archives via archive
+ *		streamer.
+ *
+ * Portions Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/bin/pg_waldump/archive_waldump.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <unistd.h>
+
+#include "access/xlog_internal.h"
+#include "common/hashfn.h"
+#include "common/logging.h"
+#include "fe_utils/simple_list.h"
+#include "pg_waldump.h"
+
+/*
+ * How many bytes should we try to read from a file at once?
+ */
+#define READ_CHUNK_SIZE				(128 * 1024)
+
+/* Structure for storing the WAL segment data from the archive */
+typedef struct ArchivedWALEntry
+{
+	uint32		status;			/* hash status */
+	XLogSegNo	segno;			/* hash key: WAL segment number */
+	TimeLineID	timeline;		/* timeline of this wal file */
+
+	StringInfoData buf;
+	bool		tmpseg_exists;	/* spill file exists? */
+
+	int			total_read;		/* total read of this WAL segment, including
+								 * buffered and temporarily written data */
+} ArchivedWALEntry;
+
+#define SH_PREFIX				ArchivedWAL
+#define SH_ELEMENT_TYPE			ArchivedWALEntry
+#define SH_KEY_TYPE				XLogSegNo
+#define SH_KEY					segno
+#define SH_HASH_KEY(tb, key)	murmurhash64((uint64) key)
+#define SH_EQUAL(tb, a, b)		(a == b)
+#define SH_GET_HASH(tb, a)		a->hash
+#define SH_SCOPE				static inline
+#define SH_RAW_ALLOCATOR		pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static ArchivedWAL_hash *ArchivedWAL_HTAB = NULL;
+
+typedef struct astreamer_waldump
+{
+	astreamer	base;
+	XLogDumpPrivate *privateInfo;
+} astreamer_waldump;
+
+static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
+static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
+											   XLogDumpPrivate *privateInfo);
+
+static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
+static void astreamer_waldump_content(astreamer *streamer,
+									  astreamer_member *member,
+									  const char *data, int len,
+									  astreamer_archive_context context);
+static void astreamer_waldump_finalize(astreamer *streamer);
+static void astreamer_waldump_free(astreamer *streamer);
+
+static bool member_is_wal_file(astreamer_waldump *mystreamer,
+							   astreamer_member *member,
+							   XLogSegNo *curSegNo,
+							   TimeLineID *curTimeline);
+
+static const astreamer_ops astreamer_waldump_ops = {
+	.content = astreamer_waldump_content,
+	.finalize = astreamer_waldump_finalize,
+	.free = astreamer_waldump_free
+};
+
+/*
+ * Returns true if the given file is a tar archive and outputs its compression
+ * algorithm.
+ */
+bool
+is_archive_file(const char *fname, pg_compress_algorithm *compression)
+{
+	int			fname_len = strlen(fname);
+	pg_compress_algorithm compress_algo;
+
+	/* Now, check the compression type of the tar */
+	if (fname_len > 4 &&
+		strcmp(fname + fname_len - 4, ".tar") == 0)
+		compress_algo = PG_COMPRESSION_NONE;
+	else if (fname_len > 4 &&
+			 strcmp(fname + fname_len - 4, ".tgz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 7 &&
+			 strcmp(fname + fname_len - 7, ".tar.gz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.lz4") == 0)
+		compress_algo = PG_COMPRESSION_LZ4;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.zst") == 0)
+		compress_algo = PG_COMPRESSION_ZSTD;
+	else
+		return false;
+
+	*compression = compress_algo;
+
+	return true;
+}
+
+/*
+ * Initializes the tar archive reader to read WAL files from the archive,
+ * creates a hash table to store them, performs quick existence checks for WAL
+ * entries in the archive and retrieves the WAL segment size, and sets up
+ * filtering criteria for relevant entries.
+ */
+void
+init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
+					pg_compress_algorithm compression)
+{
+	int			fd;
+	astreamer  *streamer;
+	ArchivedWALEntry *entry = NULL;
+	XLogLongPageHeader longhdr;
+
+	/* Open tar archive and store its file descriptor */
+	fd = open_file_in_directory(waldir, privateInfo->archive_name);
+
+	if (fd < 0)
+		pg_fatal("could not open file \"%s\"", privateInfo->archive_name);
+
+	privateInfo->archive_fd = fd;
+
+	streamer = astreamer_waldump_new(privateInfo);
+
+	/* Before that we must parse the tar archive. */
+	streamer = astreamer_tar_parser_new(streamer);
+
+	/* Before that we must decompress, if archive is compressed. */
+	if (compression == PG_COMPRESSION_GZIP)
+		streamer = astreamer_gzip_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_LZ4)
+		streamer = astreamer_lz4_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_ZSTD)
+		streamer = astreamer_zstd_decompressor_new(streamer);
+
+	privateInfo->archive_streamer = streamer;
+
+	/* Hash table storing WAL entries read from the archive */
+	ArchivedWAL_HTAB = ArchivedWAL_create(16, NULL);
+
+	/*
+	 * Verify that the archive contains valid WAL files and fetch WAL segment
+	 * size
+	 */
+	while (entry == NULL || entry->buf.len < XLOG_BLCKSZ)
+	{
+		if (read_archive_file(privateInfo, XLOG_BLCKSZ) == 0)
+			pg_fatal("could not find WAL in \"%s\" archive",
+					 privateInfo->archive_name);
+
+		entry = privateInfo->cur_wal;
+	}
+
+	/* Set WalSegSz if WAL data is successfully read */
+	longhdr = (XLogLongPageHeader) entry->buf.data;
+
+	WalSegSz = longhdr->xlp_seg_size;
+
+	if (!IsValidWalSegSize(WalSegSz))
+	{
+		pg_log_error(ngettext("invalid WAL segment size in WAL file from archive \"%s\" (%d byte)",
+							  "invalid WAL segment size in WAL file from archive \"%s\" (%d bytes)",
+							  WalSegSz),
+					 privateInfo->archive_name, WalSegSz);
+		pg_log_error_detail("The WAL segment size must be a power of two between 1 MB and 1 GB.");
+		exit(1);
+	}
+
+	/*
+	 * With the WAL segment size available, we can now initialize the
+	 * dependent start and end segment numbers.
+	 */
+	Assert(!XLogRecPtrIsInvalid(privateInfo->startptr));
+	XLByteToSeg(privateInfo->startptr, privateInfo->startSegNo, WalSegSz);
+
+	if (XLogRecPtrIsInvalid(privateInfo->endptr))
+		privateInfo->endSegNo = UINT64_MAX;
+	else
+		XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+}
+
+/*
+ * Release the archive streamer chain and close the archive file.
+ */
+void
+free_archive_reader(XLogDumpPrivate *privateInfo)
+{
+	/*
+	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
+	 * flush any remaining buffered data or to ensure the end of the tar
+	 * archive is reached. However, when decoding a WAL file, once we hit the
+	 * end LSN, any remaining WAL data in the buffer or the tar archive's
+	 * unreached end can be safely ignored.
+	 */
+	astreamer_free(privateInfo->archive_streamer);
+
+	/* Close the file. */
+	if (close(privateInfo->archive_fd) != 0)
+		pg_log_error("could not close file \"%s\": %m",
+					 privateInfo->archive_name);
+}
+
+/*
+ * Copies WAL data from astreamer to readBuff; if unavailable, fetches more
+ * from the tar archive via astreamer.
+ */
+int
+read_archive_wal_page(XLogDumpPrivate *privateInfo, XLogRecPtr targetPagePtr,
+					  Size count, char *readBuff)
+{
+	char	   *p = readBuff;
+	Size		nbytes = count;
+	XLogRecPtr	recptr = targetPagePtr;
+	XLogSegNo	segno;
+	ArchivedWALEntry *entry;
+
+	XLByteToSeg(targetPagePtr, segno, WalSegSz);
+	entry = get_archive_wal_entry(segno, privateInfo);
+
+	while (nbytes > 0)
+	{
+		char	   *buf = entry->buf.data;
+		int			len = entry->buf.len;
+
+		/* WAL record range that the buffer contains */
+		XLogRecPtr	endPtr;
+		XLogRecPtr	startPtr;
+
+		XLogSegNoOffsetToRecPtr(entry->segno, entry->total_read,
+								WalSegSz, endPtr);
+		startPtr = endPtr - len;
+
+		/*
+		 * pg_waldump may request to re-read the currently active page, but
+		 * never a page older than the current one. Therefore, any fully
+		 * consumed WAL data preceding the current page can be safely
+		 * discarded.
+		 */
+		if (recptr >= endPtr)
+		{
+			/* Discard the buffered data */
+			resetStringInfo(&entry->buf);
+			len = 0;
+
+			/*
+			 * Push back the partial page data for the current page to the
+			 * buffer, ensuring it remains available for re-reading if
+			 * requested.
+			 */
+			if (p > readBuff)
+			{
+				Assert((count - nbytes) > 0);
+				appendBinaryStringInfo(&entry->buf, readBuff, count - nbytes);
+			}
+		}
+
+		if (len > 0 && recptr > startPtr)
+		{
+			int			skipBytes = 0;
+
+			/*
+			 * The required offset is not at the start of the buffer, so skip
+			 * bytes until reaching the desired offset of the target page.
+			 */
+			skipBytes = recptr - startPtr;
+
+			buf += skipBytes;
+			len -= skipBytes;
+		}
+
+		if (len > 0)
+		{
+			int			readBytes = len >= nbytes ? nbytes : len;
+
+			/* Ensure the reading page is in the buffer */
+			Assert(recptr >= startPtr && recptr < endPtr);
+
+			memcpy(p, buf, readBytes);
+
+			/* Update state for read */
+			nbytes -= readBytes;
+			p += readBytes;
+			recptr += readBytes;
+		}
+		else
+		{
+			/*
+			 * Fetch more data; raise an error if it's not the current segment
+			 * being read by the archive streamer or if reading of the
+			 * archived file has finished.
+			 */
+			if (privateInfo->cur_wal != entry ||
+				read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+			{
+				char		fname[MAXFNAMELEN];
+
+				XLogFileName(fname, privateInfo->timeline, entry->segno,
+							 WalSegSz);
+				pg_fatal("could not read file \"%s\" from archive \"%s\": read %lld of %lld",
+						 fname, privateInfo->archive_name,
+						 (long long int) count - nbytes,
+						 (long long int) nbytes);
+			}
+		}
+	}
+
+	/*
+	 * Should have either have successfully read all the requested bytes or
+	 * reported a failure before this point.
+	 */
+	Assert(nbytes == 0);
+
+	/*
+	 * NB: We return the fixed value provided as input. Although we could
+	 * return a boolean since we either successfully read the WAL page or
+	 * raise an error, but the caller expects this value to be returned. The
+	 * routine that reads WAL pages from the physical WAL file follows the
+	 * same convention.
+	 */
+	return count;
+}
+
+/*
+ * Reads the archive file and passes it to the archive streamer for
+ * decompression.
+ */
+static int
+read_archive_file(XLogDumpPrivate *privateInfo, Size count)
+{
+	int			rc;
+	char	   *buffer;
+
+	buffer = pg_malloc(READ_CHUNK_SIZE * sizeof(uint8));
+
+	rc = read(privateInfo->archive_fd, buffer, count);
+	if (rc < 0)
+		pg_fatal("could not read file \"%s\": %m",
+				 privateInfo->archive_name);
+
+	/*
+	 * Decompress (if required), and then parse the previously read contents
+	 * of the tar file.
+	 */
+	if (rc > 0)
+		astreamer_content(privateInfo->archive_streamer, NULL,
+						  buffer, rc, ASTREAMER_UNKNOWN);
+	pg_free(buffer);
+
+	return rc;
+}
+
+/*
+ * Returns the archived WAL entry from the hash table if it exists. Otherwise,
+ * it invokes the routine to read the archived file and retrieve the entry if
+ * it is not already in hash table.
+ */
+static ArchivedWALEntry *
+get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
+{
+	ArchivedWALEntry *entry = NULL;
+	char		fname[MAXFNAMELEN];
+
+	/* Search hash table */
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry != NULL)
+		return entry;
+
+	/* Needed WAL yet to be decoded from archive, do the same */
+	while (1)
+	{
+		entry = privateInfo->cur_wal;
+
+		/* Fetch more data */
+		if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+			break;			/* archive file ended */
+
+		/*
+		 * Either, here for the first time, or the archived streamer is
+		 * reading a non-WAL file or an irrelevant WAL file.
+		 */
+		if (entry == NULL)
+			continue;
+
+		/* Found the required entry */
+		if (entry->segno == segno)
+			return entry;
+
+		/*
+		 * Ignore if the timeline is different or the current segment is not
+		 * the desired one.
+		 */
+		if (privateInfo->timeline != entry->timeline ||
+			privateInfo->startSegNo > entry->segno ||
+			privateInfo->endSegNo < entry->segno)
+		{
+			privateInfo->cur_wal = NULL;
+			continue;
+		}
+
+		/*
+		 * XXX: If the segment being read not the requested one, the data must
+		 * be buffered, as we currently lack the mechanism to write it to a
+		 * temporary file. This is a known limitation that will be fixed in the
+		 * next patch, as the buffer could grow up to the full WAL segment
+		 * size.
+		 */
+		if (segno > entry->segno)
+			continue;
+
+		/* WAL segments must be archived in order */
+		pg_log_error("WAL files are not archived in sequential order");
+		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
+							segno, entry->segno);
+		exit(1);
+	}
+
+	/* Requested WAL segment not found */
+	XLogFileName(fname, privateInfo->timeline, segno, WalSegSz);
+	pg_fatal("could not find file \"%s\" in archive", fname);
+}
+
+/*
+ * Create an astreamer that can read WAL from a tar file.
+ */
+static astreamer *
+astreamer_waldump_new(XLogDumpPrivate *privateInfo)
+{
+	astreamer_waldump *streamer;
+
+	streamer = palloc0(sizeof(astreamer_waldump));
+	*((const astreamer_ops **) &streamer->base.bbs_ops) =
+		&astreamer_waldump_ops;
+
+	streamer->privateInfo = privateInfo;
+
+	return &streamer->base;
+}
+
+/*
+ * Main entry point of the archive streamer for reading WAL data from a tar
+ * file. If a member is identified as a valid WAL file, a hash entry is created
+ * for it, and its contents are copied into that entry's buffer, making them
+ * accessible to the decoding routine.
+ */
+static void
+astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
+						  const char *data, int len,
+						  astreamer_archive_context context)
+{
+	astreamer_waldump *mystreamer = (astreamer_waldump *) streamer;
+	XLogDumpPrivate *privateInfo = mystreamer->privateInfo;
+
+	Assert(context != ASTREAMER_UNKNOWN);
+
+	switch (context)
+	{
+		case ASTREAMER_MEMBER_HEADER:
+			{
+				XLogSegNo	segno;
+				TimeLineID	timeline;
+				ArchivedWALEntry *entry;
+				bool		found;
+
+				pg_log_debug("reading \"%s\"", member->pathname);
+
+				if (!member_is_wal_file(mystreamer, member,
+										&segno, &timeline))
+					break;
+
+				entry = ArchivedWAL_insert(ArchivedWAL_HTAB, segno, &found);
+
+				/*
+				 * Shouldn't happen, but if it does, simply ignore the
+				 * duplicate WAL file.
+				 */
+				if (found)
+				{
+					pg_log_warning("ignoring duplicate WAL file found in archive: \"%s\"",
+								   member->pathname);
+					break;
+				}
+
+				initStringInfo(&entry->buf);
+				entry->timeline = timeline;
+				entry->total_read = 0;
+
+				privateInfo->cur_wal = entry;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_CONTENTS:
+			if (privateInfo->cur_wal)
+			{
+				appendBinaryStringInfo(&privateInfo->cur_wal->buf, data, len);
+				privateInfo->cur_wal->total_read += len;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_TRAILER:
+			privateInfo->cur_wal = NULL;
+			break;
+
+		case ASTREAMER_ARCHIVE_TRAILER:
+			break;
+
+		default:
+			/* Shouldn't happen. */
+			pg_fatal("unexpected state while parsing tar file");
+	}
+}
+
+/*
+ * End-of-stream processing for an astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_finalize(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+}
+
+/*
+ * Free memory associated with a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_free(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+	pfree(streamer);
+}
+
+/*
+ * Returns true if the archive member name matches the WAL naming format. If
+ * successful, it also outputs the WAL segment number, and timeline.
+ */
+static bool
+member_is_wal_file(astreamer_waldump *mystreamer, astreamer_member *member,
+				   XLogSegNo *curSegNo, TimeLineID *curTimeline)
+{
+	int			pathlen;
+	XLogSegNo	segNo;
+	TimeLineID	timeline;
+	char	   *fname;
+
+	/* We are only interested in normal files. */
+	if (member->is_directory || member->is_link)
+		return false;
+
+	pathlen = strlen(member->pathname);
+	if (pathlen < XLOG_FNAME_LEN)
+		return false;
+
+	/* WAL file could be with full path */
+	fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+	if (!IsXLogFileName(fname))
+		return false;
+
+	/*
+	 * XXX: On some systems (e.g., OpenBSD), the tar utility includes
+	 * PaxHeaders when creating an archive. These are special entries that
+	 * store extended metadata for the file entry immediately following them,
+	 * and they share the exact same name as that file.
+	 */
+	if (strstr(member->pathname, "PaxHeaders."))
+		return false;
+
+	/* Parse position from file */
+	XLogFromFileName(fname, &timeline, &segNo, WalSegSz);
+
+	*curSegNo = segNo;
+	*curTimeline = timeline;
+
+	return true;
+}
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 937e0d68841..f31e0d1cd86 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -1,6 +1,7 @@
 # Copyright (c) 2022-2025, PostgreSQL Global Development Group
 
 pg_waldump_sources = files(
+  'archive_waldump.c',
   'compat.c',
   'pg_waldump.c',
   'rmgrdesc.c',
@@ -18,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, lz4, zstd],
+  dependencies: [frontend_code, lz4, zstd, libpq],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
@@ -29,6 +30,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'TAR': tar.found() ? tar.full_path() : ''},
     'tests': [
       't/001_basic.pl',
       't/002_save_fullpage.pl',
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 2c11e0e5ca1..1eedf8e01b4 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -38,7 +38,7 @@
  * give a thought about doing the same in pg_walinspect contrib module as well.
  */
 
-int			WalSegSz;
+int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 
 static const char *progname;
 
@@ -178,7 +178,7 @@ split_path(const char *path, char **dir, char **fname)
  *
  * return a read only fd
  */
-static int
+int
 open_file_in_directory(const char *directory, const char *fname)
 {
 	int			fd = -1;
@@ -444,6 +444,45 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 	return count;
 }
 
+/*
+ * pg_waldump's XLogReaderRoutine->segment_open callback to support dumping WAL
+ * files from tar archives.
+ */
+static void
+TarWALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
+					  TimeLineID *tli_p)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->segment_close callback.
+ */
+static void
+TarWALDumpCloseSegment(XLogReaderState *state)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->page_read callback to support dumping WAL
+ * files from tar archives.
+ */
+static int
+TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				   XLogRecPtr targetPtr, char *readBuff)
+{
+	XLogDumpPrivate *private = state->private_data;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
+
+	/* Bail out if the count to be read is not valid */
+	if (count < 0)
+		return -1;
+
+	/* Read the WAL page from the archive streamer */
+	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
+}
+
 /*
  * Boolean to return whether the given WAL record matches a specific relation
  * and optionally block.
@@ -781,8 +820,8 @@ usage(void)
 	printf(_("  -F, --fork=FORK        only show records that modify blocks in fork FORK;\n"
 			 "                         valid names are main, fsm, vm, init\n"));
 	printf(_("  -n, --limit=N          number of records to display\n"));
-	printf(_("  -p, --path=PATH        directory in which to find WAL segment files or a\n"
-			 "                         directory with a ./pg_wal that contains such files\n"
+	printf(_("  -p, --path=PATH        tar archive or a directory in which to find WAL segment files or\n"
+			 "                         a directory with a ./pg_wal that contains such files\n"
 			 "                         (default: current directory, ./pg_wal, $PGDATA/pg_wal)\n"));
 	printf(_("  -q, --quiet            do not print any output, except for errors\n"));
 	printf(_("  -r, --rmgr=RMGR        only show records generated by resource manager RMGR;\n"
@@ -814,7 +853,10 @@ main(int argc, char **argv)
 	XLogRecord *record;
 	XLogRecPtr	first_record;
 	char	   *waldir = NULL;
+	char	   *walpath = NULL;
 	char	   *errormsg;
+	bool		is_archive = false;
+	pg_compress_algorithm compression;
 
 	static struct option long_options[] = {
 		{"bkp-details", no_argument, NULL, 'b'},
@@ -946,7 +988,7 @@ main(int argc, char **argv)
 				}
 				break;
 			case 'p':
-				waldir = pg_strdup(optarg);
+				walpath = pg_strdup(optarg);
 				break;
 			case 'q':
 				config.quiet = true;
@@ -1110,10 +1152,20 @@ main(int argc, char **argv)
 		goto bad_argument;
 	}
 
-	if (waldir != NULL)
+	if (walpath != NULL)
 	{
+		/* validate path points to tar archive */
+		if (is_archive_file(walpath, &compression))
+		{
+			char	   *fname = NULL;
+
+			split_path(walpath, &waldir, &fname);
+
+			private.archive_name = fname;
+			is_archive = true;
+		}
 		/* validate path points to directory */
-		if (!verify_directory(waldir))
+		else if (!verify_directory(walpath))
 		{
 			pg_log_error("could not open directory \"%s\": %m", waldir);
 			goto bad_argument;
@@ -1131,6 +1183,17 @@ main(int argc, char **argv)
 		int			fd;
 		XLogSegNo	segno;
 
+		/*
+		 * If a tar archive is passed using the --path option, all other
+		 * arguments become unnecessary.
+		 */
+		if (is_archive)
+		{
+			pg_log_error("unnecessary command-line arguments specified with tar archive (first is \"%s\")",
+						 argv[optind]);
+			goto bad_argument;
+		}
+
 		split_path(argv[optind], &directory, &fname);
 
 		if (waldir == NULL && directory != NULL)
@@ -1141,69 +1204,77 @@ main(int argc, char **argv)
 				pg_fatal("could not open directory \"%s\": %m", waldir);
 		}
 
-		waldir = identify_target_directory(waldir, fname);
-		fd = open_file_in_directory(waldir, fname);
-		if (fd < 0)
-			pg_fatal("could not open file \"%s\"", fname);
-		close(fd);
-
-		/* parse position from file */
-		XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
-
-		if (!XLogRecPtrIsValid(private.startptr))
-			XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
-		else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+		if (fname != NULL && is_archive_file(fname, &compression))
 		{
-			pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.startptr),
-						 fname);
-			goto bad_argument;
+			private.archive_name = fname;
+			is_archive = true;
 		}
-
-		/* no second file specified, set end position */
-		if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
-			XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
-
-		/* parse ENDSEG if passed */
-		if (optind + 1 < argc)
+		else
 		{
-			XLogSegNo	endsegno;
-
-			/* ignore directory, already have that */
-			split_path(argv[optind + 1], &directory, &fname);
-
+			waldir = identify_target_directory(waldir, fname);
 			fd = open_file_in_directory(waldir, fname);
 			if (fd < 0)
 				pg_fatal("could not open file \"%s\"", fname);
 			close(fd);
 
 			/* parse position from file */
-			XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+			XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
 
-			if (endsegno < segno)
-				pg_fatal("ENDSEG %s is before STARTSEG %s",
-						 argv[optind + 1], argv[optind]);
+			if (!XLogRecPtrIsValid(private.startptr))
+				XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
+			else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+			{
+				pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.startptr),
+							 fname);
+				goto bad_argument;
+			}
 
-			if (!XLogRecPtrIsValid(private.endptr))
-				XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
-										private.endptr);
+			/* no second file specified, set end position */
+			if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
+				XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
 
-			/* set segno to endsegno for check of --end */
-			segno = endsegno;
-		}
+			/* parse ENDSEG if passed */
+			if (optind + 1 < argc)
+			{
+				XLogSegNo	endsegno;
 
+				/* ignore directory, already have that */
+				split_path(argv[optind + 1], &directory, &fname);
 
-		if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
-			private.endptr != (segno + 1) * WalSegSz)
-		{
-			pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.endptr),
-						 argv[argc - 1]);
-			goto bad_argument;
+				fd = open_file_in_directory(waldir, fname);
+				if (fd < 0)
+					pg_fatal("could not open file \"%s\"", fname);
+				close(fd);
+
+				/* parse position from file */
+				XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+
+				if (endsegno < segno)
+					pg_fatal("ENDSEG %s is before STARTSEG %s",
+							 argv[optind + 1], argv[optind]);
+
+				if (!XLogRecPtrIsValid(private.endptr))
+					XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
+											private.endptr);
+
+				/* set segno to endsegno for check of --end */
+				segno = endsegno;
+			}
+
+
+			if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
+				private.endptr != (segno + 1) * WalSegSz)
+			{
+				pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.endptr),
+							 argv[argc - 1]);
+				goto bad_argument;
+			}
 		}
 	}
-	else
-		waldir = identify_target_directory(waldir, NULL);
+	else if (!is_archive)
+		waldir = identify_target_directory(walpath, NULL);
 
 	/* we don't know what to print */
 	if (!XLogRecPtrIsValid(private.startptr))
@@ -1215,12 +1286,36 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
-	xlogreader_state =
-		XLogReaderAllocate(WalSegSz, waldir,
-						   XL_ROUTINE(.page_read = WALDumpReadPage,
-									  .segment_open = WALDumpOpenSegment,
-									  .segment_close = WALDumpCloseSegment),
-						   &private);
+	if (is_archive)
+	{
+		/*
+		 * A NULL WAL directory indicates that the archive file is located in
+		 * the current working directory of the pg_waldump execution
+		 */
+		waldir = waldir ? pg_strdup(waldir) : pg_strdup(".");
+
+		/* Set up for reading tar file */
+		init_archive_reader(&private, waldir, compression);
+
+		/* Routine to decode WAL files in tar archive */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = TarWALDumpReadPage,
+										  .segment_open = TarWALDumpOpenSegment,
+										  .segment_close = TarWALDumpCloseSegment),
+							   &private);
+	}
+	else
+	{
+		/* Routine to decode WAL files */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = WALDumpReadPage,
+										  .segment_open = WALDumpOpenSegment,
+										  .segment_close = WALDumpCloseSegment),
+							   &private);
+	}
+
 	if (!xlogreader_state)
 		pg_fatal("out of memory while allocating a WAL reading processor");
 
@@ -1329,6 +1424,9 @@ main(int argc, char **argv)
 
 	XLogReaderFree(xlogreader_state);
 
+	if (is_archive)
+		free_archive_reader(&private);
+
 	return EXIT_SUCCESS;
 
 bad_argument:
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 926d529f9d6..ec7a33d40e0 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -12,9 +12,13 @@
 #define PG_WALDUMP_H
 
 #include "access/xlogdefs.h"
+#include "fe_utils/astreamer.h"
 
 extern int	WalSegSz;
 
+/* Forward declaration */
+struct ArchivedWALEntry;
+
 /* Contains the necessary information to drive WAL decoding */
 typedef struct XLogDumpPrivate
 {
@@ -22,6 +26,36 @@ typedef struct XLogDumpPrivate
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	bool		endptr_reached;
+
+	/* Fields required to read WAL from archive */
+	char	   *archive_name;	/* Tar archive name */
+	int			archive_fd;		/* File descriptor for the open tar file */
+
+	astreamer  *archive_streamer;
+
+	/* What the archive streamer is currently reading */
+	struct ArchivedWALEntry *cur_wal;
+
+	/*
+	 * Although these values can be easily derived from startptr and endptr,
+	 * doing so repeatedly for each archived member would be inefficient, as
+	 * it would involve recalculating and filtering out irrelevant WAL
+	 * segments.
+	 */
+	XLogSegNo	startSegNo;
+	XLogSegNo	endSegNo;
 } XLogDumpPrivate;
 
+extern int	open_file_in_directory(const char *directory, const char *fname);
+
+extern bool is_archive_file(const char *fname,
+							pg_compress_algorithm *compression);
+extern void init_archive_reader(XLogDumpPrivate *privateInfo,
+								const char *waldir,
+								pg_compress_algorithm compression);
+extern void free_archive_reader(XLogDumpPrivate *privateInfo);
+extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
+								  XLogRecPtr targetPagePtr,
+								  Size count, char *readBuff);
+
 #endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index c8fdc7cb4f3..b12bbc6f95b 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -3,10 +3,13 @@
 
 use strict;
 use warnings FATAL => 'all';
+use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
 
+my $tar = $ENV{TAR};
+
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
 program_options_handling_ok('pg_waldump');
@@ -235,7 +238,7 @@ command_like(
 sub test_pg_waldump
 {
 	local $Test::Builder::Level = $Test::Builder::Level + 1;
-	my @opts = @_;
+	my ($path, @opts) = @_;
 
 	my ($stdout, $stderr);
 
@@ -243,6 +246,7 @@ sub test_pg_waldump
 		'pg_waldump',
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
+		'--path' => $path,
 		@opts
 	  ],
 	  '>' => \$stdout,
@@ -254,11 +258,50 @@ sub test_pg_waldump
 	return @lines;
 }
 
-my @lines;
+# Create a tar archive, sorting the file order
+sub generate_archive
+{
+	my ($archive, $directory, $compression_flags) = @_;
+
+	my @files;
+	opendir my $dh, $directory or die "opendir: $!";
+	while (my $entry = readdir $dh) {
+		# Skip '.' and '..'
+		next if $entry eq '.' || $entry eq '..';
+		push @files, $entry;
+	}
+	closedir $dh;
+
+	@files = sort @files;
+
+	# move into the WAL directory before archiving files
+	my $cwd = getcwd;
+	chdir($directory) || die "chdir: $!";
+	command_ok([$tar, $compression_flags, $archive, @files]);
+	chdir($cwd) || die "chdir: $!";
+}
+
+my $tmp_dir = PostgreSQL::Test::Utils::tempdir_short();
 
 my @scenarios = (
 	{
-		'path' => $node->data_dir
+		'path' => $node->data_dir,
+		'is_archive' => 0,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar",
+		'compression_method' => 'none',
+		'compression_flags' => '-cf',
+		'is_archive' => 1,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar.gz",
+		'compression_method' => 'gzip',
+		'compression_flags' => '-czf',
+		'is_archive' => 1,
+		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
 	});
 
 for my $scenario (@scenarios)
@@ -267,6 +310,19 @@ for my $scenario (@scenarios)
 
 	SKIP:
 	{
+		skip "tar command is not available", 3
+		  if !defined $tar;
+		skip "$scenario->{'compression_method'} compression not supported by this build", 3
+		  if !$scenario->{'enabled'} && $scenario->{'is_archive'};
+
+		  # create pg_wal archive
+		  if ($scenario->{'is_archive'})
+		  {
+			  generate_archive($path,
+				  $node->data_dir . '/pg_wal',
+				  $scenario->{'compression_flags'});
+		  }
+
 		command_fails_like(
 			[ 'pg_waldump', '--path' => $path ],
 			qr/error: no start WAL location given/,
@@ -298,38 +354,42 @@ for my $scenario (@scenarios)
 			qr/error: error in WAL record at/,
 			'errors are shown with --quiet');
 
-		@lines = test_pg_waldump('--path' => $path);
+		my @lines;
+		@lines = test_pg_waldump($path);
 		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		@lines = test_pg_waldump($path, '--limit' => 6);
 		is(@lines, 6, 'limit option observed');
 
-		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		@lines = test_pg_waldump($path, '--fullpage');
 		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats');
+		@lines = test_pg_waldump($path, '--stats');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		@lines = test_pg_waldump($path, '--stats=record');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		@lines = test_pg_waldump($path, '--rmgr' => 'Btree');
 		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		@lines = test_pg_waldump($path, '--fork' => 'init');
 		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
 		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
 			0, 'only lines for selected relation');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
 			'--block' => 1);
 		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+
+		# Cleanup.
+		unlink $path if $scenario->{'is_archive'};
 	}
 }
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 57a8f0366a5..981cdb69175 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -139,6 +139,8 @@ ArchiveOpts
 ArchiveShutdownCB
 ArchiveStartupCB
 ArchiveStreamState
+ArchivedWALEntry
+ArchivedWAL_hash
 ArchiverOutput
 ArchiverStage
 ArrayAnalyzeExtraData
@@ -3466,6 +3468,7 @@ astreamer_recovery_injector
 astreamer_tar_archiver
 astreamer_tar_parser
 astreamer_verify
+astreamer_waldump
 astreamer_zstd_frame
 auth_password_hook_typ
 autovac_table
-- 
2.47.1

From 4815eb6ef2182b8ef5512bed842aea9821502853 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 6 Nov 2025 13:48:33 +0530
Subject: [PATCH v9 5/8] pg_waldump: Remove the restriction on the order of
 archived WAL files.

With previous patch, pg_waldump would stop decoding if WAL files were
not in the required sequence. With this patch, decoding will now
continue.  Any WAL file that is out of order will be written to a
temporary location, from which it will be read later. Once a temporary
file has been read, it will be removed.
---
 doc/src/sgml/ref/pg_waldump.sgml     |   8 +-
 src/bin/pg_waldump/archive_waldump.c | 233 ++++++++++++++++++++++++---
 src/bin/pg_waldump/pg_waldump.c      |  41 ++++-
 src/bin/pg_waldump/pg_waldump.h      |   4 +
 src/bin/pg_waldump/t/001_basic.pl    |   3 +-
 5 files changed, 265 insertions(+), 24 deletions(-)

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index d004bb0f67e..25f96f86168 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -149,8 +149,12 @@ PostgreSQL documentation
         of <envar>PGDATA</envar>.
        </para>
        <para>
-        If a tar archive is provided, its WAL segment files must be in
-        sequential order; otherwise, an error will be reported.
+        If a tar archive is provided and its WAL segment files are not in
+        sequential order, those files will be written to a temporary directory
+        named starting with <filename>waldump/</filename>. This directory will be
+        created inside the directory specified by the <envar>TMPDIR</envar>
+        environment variable if it is set; otherwise, it will be created within
+        the same directory as the tar archive.
        </para>
       </listitem>
      </varlistentry>
diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
index 63141dc2ee2..2038876a516 100644
--- a/src/bin/pg_waldump/archive_waldump.c
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -17,6 +17,7 @@
 #include <unistd.h>
 
 #include "access/xlog_internal.h"
+#include "common/file_perm.h"
 #include "common/hashfn.h"
 #include "common/logging.h"
 #include "fe_utils/simple_list.h"
@@ -27,6 +28,9 @@
  */
 #define READ_CHUNK_SIZE				(128 * 1024)
 
+/* Temporary exported WAL file directory */
+static char *TmpWalSegDir = NULL;
+
 /* Structure for storing the WAL segment data from the archive */
 typedef struct ArchivedWALEntry
 {
@@ -65,6 +69,11 @@ typedef struct astreamer_waldump
 static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
 static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
 											   XLogDumpPrivate *privateInfo);
+static void setup_tmpseg_dir(const char *waldir);
+static void cleanup_tmpseg_dir_atexit(void);
+
+static FILE *prepare_tmp_write(XLogSegNo segno);
+static void perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file);
 
 static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
 static void astreamer_waldump_content(astreamer *streamer,
@@ -120,10 +129,11 @@ is_archive_file(const char *fname, pg_compress_algorithm *compression)
 }
 
 /*
- * Initializes the tar archive reader to read WAL files from the archive,
- * creates a hash table to store them, performs quick existence checks for WAL
- * entries in the archive and retrieves the WAL segment size, and sets up
- * filtering criteria for relevant entries.
+ * Initializes the tar archive reader, creates a hash table for WAL entries,
+ * checks for existing valid WAL segments in the archive file and retrieves the
+ * segment size, and sets up filters for relevant entries. It also configures a
+ * temporary directory for out-of-order WAL data and registers an exit callback
+ * to clean up temporary files.
  */
 void
 init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
@@ -199,6 +209,13 @@ init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
 		privateInfo->endSegNo = UINT64_MAX;
 	else
 		XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+
+	/*
+	 * Setup temporary directory to store WAL segments and set up an exit
+	 * callback to remove it upon completion.
+	 */
+	setup_tmpseg_dir(waldir);
+	atexit(cleanup_tmpseg_dir_atexit);
 }
 
 /*
@@ -374,13 +391,16 @@ read_archive_file(XLogDumpPrivate *privateInfo, Size count)
 /*
  * Returns the archived WAL entry from the hash table if it exists. Otherwise,
  * it invokes the routine to read the archived file and retrieve the entry if
- * it is not already in hash table.
+ * it is not already present in the hash table. If the archive streamer happens
+ * to be reading a WAL from archive file that is not currently needed, that WAL
+ * data is written to a temporary file.
  */
 static ArchivedWALEntry *
 get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 {
 	ArchivedWALEntry *entry = NULL;
 	char		fname[MAXFNAMELEN];
+	FILE	   *write_fp = NULL;
 
 	/* Search hash table */
 	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
@@ -394,8 +414,11 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 		entry = privateInfo->cur_wal;
 
 		/* Fetch more data */
-		if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
-			break;			/* archive file ended */
+		if (entry == NULL || entry->buf.len == 0)
+		{
+			if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+				break;			/* archive file ended */
+		}
 
 		/*
 		 * Either, here for the first time, or the archived streamer is
@@ -421,20 +444,31 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 		}
 
 		/*
-		 * XXX: If the segment being read not the requested one, the data must
-		 * be buffered, as we currently lack the mechanism to write it to a
-		 * temporary file. This is a known limitation that will be fixed in the
-		 * next patch, as the buffer could grow up to the full WAL segment
-		 * size.
+		 * Archive streamer is currently reading a file that isn't the one
+		 * asked for, but it's required for a future feature. It should be
+		 * written to a temporary location for retrieval when needed.
 		 */
-		if (segno > entry->segno)
-			continue;
 
-		/* WAL segments must be archived in order */
-		pg_log_error("WAL files are not archived in sequential order");
-		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
-							segno, entry->segno);
-		exit(1);
+		/* Create a temporary file if one does not already exist */
+		if (!entry->tmpseg_exists)
+		{
+			write_fp = prepare_tmp_write(entry->segno);
+			entry->tmpseg_exists = true;
+		}
+
+		/* Flush data from the buffer to the file */
+		perform_tmp_write(entry->segno, &entry->buf, write_fp);
+		resetStringInfo(&entry->buf);
+
+		/*
+		 * The change in the current segment entry indicates that the reading
+		 * of this file has ended.
+		 */
+		if (entry != privateInfo->cur_wal && write_fp != NULL)
+		{
+			fclose(write_fp);
+			write_fp = NULL;
+		}
 	}
 
 	/* Requested WAL segment not found */
@@ -443,7 +477,166 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 }
 
 /*
- * Create an astreamer that can read WAL from a tar file.
+ * Set up a temporary directory to temporarily store WAL segments.
+ */
+static void
+setup_tmpseg_dir(const char *waldir)
+{
+	char	   *template;
+
+	/*
+	 * Use the directory specified by the TMPDIR environment variable. If it's
+	 * not set, use the provided WAL directory to extract WAL file
+	 * temporarily.
+	 */
+	template = psprintf("%s/waldump_tmp-XXXXXX",
+						getenv("TMPDIR") ? getenv("TMPDIR") : waldir);
+	TmpWalSegDir = mkdtemp(template);
+
+	if (TmpWalSegDir == NULL)
+		pg_fatal("could not create directory \"%s\": %m", template);
+
+	canonicalize_path(TmpWalSegDir);
+
+	pg_log_debug("created directory \"%s\"", TmpWalSegDir);
+}
+
+/*
+ * Removes the temporarily store WAL segments, if any, at exiting.
+ */
+static void
+cleanup_tmpseg_dir_atexit(void)
+{
+	ArchivedWAL_iterator it;
+	ArchivedWALEntry *entry;
+
+	/* Remove temporary segments */
+	ArchivedWAL_start_iterate(ArchivedWAL_HTAB, &it);
+	while ((entry = ArchivedWAL_iterate(ArchivedWAL_HTAB, &it)) != NULL)
+	{
+		if (entry->tmpseg_exists)
+		{
+			remove_tmp_walseg(entry->segno, false);
+			entry->tmpseg_exists = false;
+		}
+	}
+
+	/* Remove temporary directory */
+	if (rmdir(TmpWalSegDir) == 0)
+		pg_log_debug("removed directory \"%s\"", TmpWalSegDir);
+}
+
+/*
+ * Generate the temporary WAL file path.
+ *
+ * Note that the caller is responsible to pfree it.
+ */
+char *
+get_tmp_walseg_path(XLogSegNo segno)
+{
+	char	   *fpath = (char *) palloc(MAXPGPATH);
+
+	Assert(TmpWalSegDir);
+
+	snprintf(fpath, MAXPGPATH, "%s/%08X%08X",
+			 TmpWalSegDir,
+			 (uint32) (segno / XLogSegmentsPerXLogId(WalSegSz)),
+			 (uint32) (segno % XLogSegmentsPerXLogId(WalSegSz)));
+
+	return fpath;
+}
+
+/*
+ * Routine to check whether a temporary file exists for the corresponding WAL
+ * segment number.
+ */
+bool
+tmp_walseg_exists(XLogSegNo segno)
+{
+	ArchivedWALEntry *entry;
+
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry == NULL)
+		return false;
+
+	return entry->tmpseg_exists;
+}
+
+/*
+ * Create an empty placeholder file and return its handle.
+ */
+static FILE *
+prepare_tmp_write(XLogSegNo segno)
+{
+	FILE	   *file;
+	char	   *fpath;
+
+	fpath = get_tmp_walseg_path(segno);
+
+	/* Create an empty placeholder */
+	file = fopen(fpath, PG_BINARY_W);
+	if (file == NULL)
+		pg_fatal("could not create file \"%s\": %m", fpath);
+
+#ifndef WIN32
+	if (chmod(fpath, pg_file_create_mode))
+		pg_fatal("could not set permissions on file \"%s\": %m",
+				 fpath);
+#endif
+
+	pg_log_debug("temporarily exporting file \"%s\"", fpath);
+	pfree(fpath);
+
+	return file;
+}
+
+/*
+ * Write buffer data to the given file handle.
+ */
+static void
+perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file)
+{
+	Assert(file);
+
+	errno = 0;
+	if (buf->len > 0 && fwrite(buf->data, buf->len, 1, file) != 1)
+	{
+		/*
+		 * If write didn't set errno, assume problem is no disk space
+		 */
+		if (errno == 0)
+			errno = ENOSPC;
+		pg_fatal("could not write to file \"%s\": %m",
+				 get_tmp_walseg_path(segno));
+	}
+}
+
+/*
+ * Remove temporary file
+ */
+void
+remove_tmp_walseg(XLogSegNo segno, bool update_entry)
+{
+	char	   *fpath = get_tmp_walseg_path(segno);
+
+	if (unlink(fpath) == 0)
+		pg_log_debug("removed file \"%s\"", fpath);
+	pfree(fpath);
+
+	/* Update entry if requested */
+	if (update_entry)
+	{
+		ArchivedWALEntry *entry;
+
+		entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+		Assert(entry != NULL);
+		entry->tmpseg_exists = false;
+	}
+}
+
+/*
+ * Create an astreamer that can read WAL from tar file.
  */
 static astreamer *
 astreamer_waldump_new(XLogDumpPrivate *privateInfo)
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 1eedf8e01b4..9179f3ea4c4 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -474,12 +474,51 @@ TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 {
 	XLogDumpPrivate *private = state->private_data;
 	int			count = required_read_len(private, targetPagePtr, reqLen);
+	XLogSegNo	nextSegNo;
 
 	/* Bail out if the count to be read is not valid */
 	if (count < 0)
 		return -1;
 
-	/* Read the WAL page from the archive streamer */
+	/*
+	 * If the target page is in a different segment, first check for the WAL
+	 * segment's physical existence in the temporary directory.
+	 */
+	nextSegNo = state->seg.ws_segno;
+	if (!XLByteInSeg(targetPagePtr, nextSegNo, WalSegSz))
+	{
+		if (state->seg.ws_file >= 0)
+		{
+			close(state->seg.ws_file);
+			state->seg.ws_file = -1;
+
+			/* Remove this file, as it is no longer needed. */
+			remove_tmp_walseg(nextSegNo, true);
+		}
+
+		XLByteToSeg(targetPagePtr, nextSegNo, WalSegSz);
+		state->seg.ws_tli = private->timeline;
+		state->seg.ws_segno = nextSegNo;
+
+		/*
+		 * If the next segment exists, open it and continue reading from there
+		 */
+		if (tmp_walseg_exists(nextSegNo))
+		{
+			char	   *fpath;
+
+			fpath = get_tmp_walseg_path(nextSegNo);
+			state->seg.ws_file = open(fpath, O_RDONLY | PG_BINARY, 0);
+			pfree(fpath);
+		}
+	}
+
+	/* Continue reading from the open WAL segment, if any */
+	if (state->seg.ws_file >= 0)
+		return WALDumpReadPage(state, targetPagePtr, count, targetPtr,
+							   readBuff);
+
+	/* Otherwise, read the WAL page from the archive streamer */
 	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
 }
 
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index ec7a33d40e0..03e02625ba1 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -58,4 +58,8 @@ extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
 								  XLogRecPtr targetPagePtr,
 								  Size count, char *readBuff);
 
+extern char *get_tmp_walseg_path(XLogSegNo segno);
+extern bool tmp_walseg_exists(XLogSegNo segno);
+extern void remove_tmp_walseg(XLogSegNo segno, bool update_entry);
+
 #endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index b12bbc6f95b..d752b5dd656 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -7,6 +7,7 @@ use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
+use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
 
@@ -272,7 +273,7 @@ sub generate_archive
 	}
 	closedir $dh;
 
-	@files = sort @files;
+	@files = shuffle @files;
 
 	# move into the WAL directory before archiving files
 	my $cwd = getcwd;
-- 
2.47.1

From d4199456b4941dab2dd6dc6326b18045f5297e41 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 14:47:43 +0530
Subject: [PATCH v9 6/8] pg_verifybackup: Delay default WAL directory
 preparation.

We are not sure whether to parse WAL from a directory or an archive
until the backup format is known. Therefore, we delay preparing the
default WAL directory until the point of parsing. This delay is
harmless, as the WAL directory is not used elsewhere.
---
 src/bin/pg_verifybackup/pg_verifybackup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 8d5befa947f..a502e795b2e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -285,10 +285,6 @@ main(int argc, char **argv)
 		manifest_path = psprintf("%s/backup_manifest",
 								 context.backup_directory);
 
-	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
-
 	/*
 	 * Try to read the manifest. We treat any errors encountered while parsing
 	 * the manifest as fatal; there doesn't seem to be much point in trying to
@@ -368,6 +364,10 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
+	/* By default, look for the WAL in the backup directory, too. */
+	if (wal_directory == NULL)
+		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
-- 
2.47.1

From cf5d6388a7ddbb2abf26d7749ff947e3338dbe99 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 25 Nov 2025 17:32:14 +0530
Subject: [PATCH v9 7/8] pg_verifybackup: Rename the wal-directory switch to
 wal-path

With previous patches to pg_waldump can now decode WAL directly from
tar files.  This means you'll be able to specify a tar archive path
instead of a traditional WAL directory.

To keep things consistent and more versatile, we should also
generalize the input switch for pg_verifybackup. It should accept
either a directory or a tar file path that contains WALs. This change
will also aligning it with the existing manifest-path switch naming.

== NOTE ==
  The corresponding PO files require updating due to this change.
---
 doc/src/sgml/ref/pg_verifybackup.sgml     |  2 +-
 src/bin/pg_verifybackup/pg_verifybackup.c | 22 +++++++++++-----------
 src/bin/pg_verifybackup/t/007_wal.pl      |  4 ++--
 3 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index 61c12975e4a..e9b8bfd51b1 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -261,7 +261,7 @@ PostgreSQL documentation
 
      <varlistentry>
       <term><option>-w <replaceable class="parameter">path</replaceable></option></term>
-      <term><option>--wal-directory=<replaceable class="parameter">path</replaceable></option></term>
+      <term><option>--wal-path=<replaceable class="parameter">path</replaceable></option></term>
       <listitem>
        <para>
         Try to parse WAL files stored in the specified directory, rather than
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index a502e795b2e..9fcd6be004e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -93,7 +93,7 @@ static void verify_file_checksum(verifier_context *context,
 								 uint8 *buffer);
 static void parse_required_wal(verifier_context *context,
 							   char *pg_waldump_path,
-							   char *wal_directory);
+							   char *wal_path);
 static astreamer *create_archive_verifier(verifier_context *context,
 										  char *archive_name,
 										  Oid tblspc_oid,
@@ -126,7 +126,7 @@ main(int argc, char **argv)
 		{"progress", no_argument, NULL, 'P'},
 		{"quiet", no_argument, NULL, 'q'},
 		{"skip-checksums", no_argument, NULL, 's'},
-		{"wal-directory", required_argument, NULL, 'w'},
+		{"wal-path", required_argument, NULL, 'w'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -135,7 +135,7 @@ main(int argc, char **argv)
 	char	   *manifest_path = NULL;
 	bool		no_parse_wal = false;
 	bool		quiet = false;
-	char	   *wal_directory = NULL;
+	char	   *wal_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -221,8 +221,8 @@ main(int argc, char **argv)
 				context.skip_checksums = true;
 				break;
 			case 'w':
-				wal_directory = pstrdup(optarg);
-				canonicalize_path(wal_directory);
+				wal_path = pstrdup(optarg);
+				canonicalize_path(wal_path);
 				break;
 			default:
 				/* getopt_long already emitted a complaint */
@@ -365,15 +365,15 @@ main(int argc, char **argv)
 		verify_backup_checksums(&context);
 
 	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+	if (wal_path == NULL)
+		wal_path = psprintf("%s/pg_wal", context.backup_directory);
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
 	 */
 	if (!no_parse_wal)
-		parse_required_wal(&context, pg_waldump_path, wal_directory);
+		parse_required_wal(&context, pg_waldump_path, wal_path);
 
 	/*
 	 * If everything looks OK, tell the user this, unless we were asked to
@@ -1198,7 +1198,7 @@ verify_file_checksum(verifier_context *context, manifest_file *m,
  */
 static void
 parse_required_wal(verifier_context *context, char *pg_waldump_path,
-				   char *wal_directory)
+				   char *wal_path)
 {
 	manifest_data *manifest = context->manifest;
 	manifest_wal_range *this_wal_range = manifest->first_wal_range;
@@ -1208,7 +1208,7 @@ parse_required_wal(verifier_context *context, char *pg_waldump_path,
 		char	   *pg_waldump_cmd;
 
 		pg_waldump_cmd = psprintf("\"%s\" --quiet --path=\"%s\" --timeline=%u --start=%X/%08X --end=%X/%08X\n",
-								  pg_waldump_path, wal_directory, this_wal_range->tli,
+								  pg_waldump_path, wal_path, this_wal_range->tli,
 								  LSN_FORMAT_ARGS(this_wal_range->start_lsn),
 								  LSN_FORMAT_ARGS(this_wal_range->end_lsn));
 		fflush(NULL);
@@ -1376,7 +1376,7 @@ usage(void)
 	printf(_("  -P, --progress              show progress information\n"));
 	printf(_("  -q, --quiet                 do not print any output, except for errors\n"));
 	printf(_("  -s, --skip-checksums        skip checksum verification\n"));
-	printf(_("  -w, --wal-directory=PATH    use specified path for WAL files\n"));
+	printf(_("  -w, --wal-path=PATH         use specified path for WAL files\n"));
 	printf(_("  -V, --version               output version information, then exit\n"));
 	printf(_("  -?, --help                  show this help, then exit\n"));
 	printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
diff --git a/src/bin/pg_verifybackup/t/007_wal.pl b/src/bin/pg_verifybackup/t/007_wal.pl
index babc4f0a86b..b07f80719b0 100644
--- a/src/bin/pg_verifybackup/t/007_wal.pl
+++ b/src/bin/pg_verifybackup/t/007_wal.pl
@@ -42,10 +42,10 @@ command_ok([ 'pg_verifybackup', '--no-parse-wal', $backup_path ],
 command_ok(
 	[
 		'pg_verifybackup',
-		'--wal-directory' => $relocated_pg_wal,
+		'--wal-path' => $relocated_pg_wal,
 		$backup_path
 	],
-	'--wal-directory can be used to specify WAL directory');
+	'--wal-path can be used to specify WAL directory');
 
 # Move directory back to original location.
 rename($relocated_pg_wal, $original_pg_wal) || die "rename pg_wal back: $!";
-- 
2.47.1

From b56d51b9094b3e9adeab3480a1c81d47c5a07bbd Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 25 Nov 2025 17:34:26 +0530
Subject: [PATCH v9 8/8] pg_verifybackup: enabled WAL parsing for tar-format
 backup

Now that pg_waldump supports decoding from tar archives, we should
leverage this functionality to remove the previous restriction on WAL
parsing for tar-backed formats.
---
 doc/src/sgml/ref/pg_verifybackup.sgml         |  5 +-
 src/bin/pg_verifybackup/pg_verifybackup.c     | 66 +++++++++++++------
 src/bin/pg_verifybackup/t/002_algorithm.pl    |  4 --
 src/bin/pg_verifybackup/t/003_corruption.pl   |  4 +-
 src/bin/pg_verifybackup/t/008_untar.pl        |  5 +-
 src/bin/pg_verifybackup/t/010_client_untar.pl |  5 +-
 6 files changed, 50 insertions(+), 39 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index e9b8bfd51b1..16b50b5a4df 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -36,10 +36,7 @@ PostgreSQL documentation
    <literal>backup_manifest</literal> generated by the server at the time
    of the backup. The backup may be stored either in the "plain" or the "tar"
    format; this includes tar-format backups compressed with any algorithm
-   supported by <application>pg_basebackup</application>. However, at present,
-   <literal>WAL</literal> verification is supported only for plain-format
-   backups. Therefore, if the backup is stored in tar-format, the
-   <literal>-n, --no-parse-wal</literal> option should be used.
+   supported by <application>pg_basebackup</application>.
   </para>
 
   <para>
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 9fcd6be004e..40ec24c5984 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -74,7 +74,9 @@ pg_noreturn static void report_manifest_error(JsonManifestParseContext *context,
 											  const char *fmt,...)
 			pg_attribute_printf(2, 3);
 
-static void verify_tar_backup(verifier_context *context, DIR *dir);
+static void verify_tar_backup(verifier_context *context, DIR *dir,
+							  char **base_archive_path,
+							  char **wal_archive_path);
 static void verify_plain_backup_directory(verifier_context *context,
 										  char *relpath, char *fullpath,
 										  DIR *dir);
@@ -83,7 +85,9 @@ static void verify_plain_backup_file(verifier_context *context, char *relpath,
 static void verify_control_file(const char *controlpath,
 								uint64 manifest_system_identifier);
 static void precheck_tar_backup_file(verifier_context *context, char *relpath,
-									 char *fullpath, SimplePtrList *tarfiles);
+									 char *fullpath, SimplePtrList *tarfiles,
+									 char **base_archive_path,
+									 char **wal_archive_path);
 static void verify_tar_file(verifier_context *context, char *relpath,
 							char *fullpath, astreamer *streamer);
 static void report_extra_backup_files(verifier_context *context);
@@ -136,6 +140,8 @@ main(int argc, char **argv)
 	bool		no_parse_wal = false;
 	bool		quiet = false;
 	char	   *wal_path = NULL;
+	char	   *base_archive_path = NULL;
+	char	   *wal_archive_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -327,17 +333,6 @@ main(int argc, char **argv)
 		pfree(path);
 	}
 
-	/*
-	 * XXX: In the future, we should consider enhancing pg_waldump to read WAL
-	 * files from an archive.
-	 */
-	if (!no_parse_wal && context.format == 't')
-	{
-		pg_log_error("pg_waldump cannot read tar files");
-		pg_log_error_hint("You must use -n/--no-parse-wal when verifying a tar-format backup.");
-		exit(1);
-	}
-
 	/*
 	 * Perform the appropriate type of verification appropriate based on the
 	 * backup format. This will close 'dir'.
@@ -346,7 +341,7 @@ main(int argc, char **argv)
 		verify_plain_backup_directory(&context, NULL, context.backup_directory,
 									  dir);
 	else
-		verify_tar_backup(&context, dir);
+		verify_tar_backup(&context, dir, &base_archive_path, &wal_archive_path);
 
 	/*
 	 * The "matched" flag should now be set on every entry in the hash table.
@@ -364,9 +359,28 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
-	/* By default, look for the WAL in the backup directory, too. */
+	/*
+	 * By default, WAL files are expected to be found in the backup directory
+	 * for plain-format backups. In the case of tar-format backups, if a
+	 * separate WAL archive is not found, the WAL files are most likely
+	 * included within the main data directory archive.
+	 */
 	if (wal_path == NULL)
-		wal_path = psprintf("%s/pg_wal", context.backup_directory);
+	{
+		if (context.format == 'p')
+			wal_path = psprintf("%s/pg_wal", context.backup_directory);
+		else if (wal_archive_path)
+			wal_path = wal_archive_path;
+		else if (base_archive_path)
+			wal_path = base_archive_path;
+		else
+		{
+			pg_log_error("WAL archive not found");
+			pg_log_error_hint("Specify the correct path using the option -w/--wal-path.  "
+							  "Or you must use -n/--no-parse-wal when verifying a tar-format backup.");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
@@ -787,7 +801,8 @@ verify_control_file(const char *controlpath, uint64 manifest_system_identifier)
  * close when we're done with it.
  */
 static void
-verify_tar_backup(verifier_context *context, DIR *dir)
+verify_tar_backup(verifier_context *context, DIR *dir, char **base_archive_path,
+				  char **wal_archive_path)
 {
 	struct dirent *dirent;
 	SimplePtrList tarfiles = {NULL, NULL};
@@ -816,7 +831,8 @@ verify_tar_backup(verifier_context *context, DIR *dir)
 			char	   *fullpath;
 
 			fullpath = psprintf("%s/%s", context->backup_directory, filename);
-			precheck_tar_backup_file(context, filename, fullpath, &tarfiles);
+			precheck_tar_backup_file(context, filename, fullpath, &tarfiles,
+									 base_archive_path, wal_archive_path);
 			pfree(fullpath);
 		}
 	}
@@ -875,11 +891,13 @@ verify_tar_backup(verifier_context *context, DIR *dir)
  *
  * The arguments to this function are mostly the same as the
  * verify_plain_backup_file. The additional argument outputs a list of valid
- * tar files.
+ * tar files, along with the full paths to the main archive and the WAL
+ * directory archive.
  */
 static void
 precheck_tar_backup_file(verifier_context *context, char *relpath,
-						 char *fullpath, SimplePtrList *tarfiles)
+						 char *fullpath, SimplePtrList *tarfiles,
+						 char **base_archive_path, char **wal_archive_path)
 {
 	struct stat sb;
 	Oid			tblspc_oid = InvalidOid;
@@ -918,9 +936,17 @@ precheck_tar_backup_file(verifier_context *context, char *relpath,
 	 * extension such as .gz, .lz4, or .zst.
 	 */
 	if (strncmp("base", relpath, 4) == 0)
+	{
 		suffix = relpath + 4;
+
+		*base_archive_path = pstrdup(fullpath);
+	}
 	else if (strncmp("pg_wal", relpath, 6) == 0)
+	{
 		suffix = relpath + 6;
+
+		*wal_archive_path = pstrdup(fullpath);
+	}
 	else
 	{
 		/* Expected a <tablespaceoid>.tar file here. */
diff --git a/src/bin/pg_verifybackup/t/002_algorithm.pl b/src/bin/pg_verifybackup/t/002_algorithm.pl
index ae16c11bc4d..4f284a9e828 100644
--- a/src/bin/pg_verifybackup/t/002_algorithm.pl
+++ b/src/bin/pg_verifybackup/t/002_algorithm.pl
@@ -30,10 +30,6 @@ sub test_checksums
 	{
 		# Add switch to get a tar-format backup
 		push @backup, ('--format' => 'tar');
-
-		# Add switch to skip WAL verification, which is not yet supported for
-		# tar-format backups
-		push @verify, ('--no-parse-wal');
 	}
 
 	# A backup with a bogus algorithm should fail.
diff --git a/src/bin/pg_verifybackup/t/003_corruption.pl b/src/bin/pg_verifybackup/t/003_corruption.pl
index 1dd60f709cf..f1ebdbb46b4 100644
--- a/src/bin/pg_verifybackup/t/003_corruption.pl
+++ b/src/bin/pg_verifybackup/t/003_corruption.pl
@@ -193,10 +193,8 @@ for my $scenario (@scenario)
 			command_ok([ $tar, '-cf' => "$tar_backup_path/base.tar", '.' ]);
 			chdir($cwd) || die "chdir: $!";
 
-			# Now check that the backup no longer verifies. We must use -n
-			# here, because pg_waldump can't yet read WAL from a tarfile.
 			command_fails_like(
-				[ 'pg_verifybackup', '--no-parse-wal', $tar_backup_path ],
+				[ 'pg_verifybackup', $tar_backup_path ],
 				$scenario->{'fails_like'},
 				"corrupt backup fails verification: $name");
 
diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index bc3d6b352ad..09079a94fee 100644
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -47,7 +47,6 @@ my $tsoid = $primary->safe_psql(
 		SELECT oid FROM pg_tablespace WHERE spcname = 'regress_ts1'));
 
 my $backup_path = $primary->backup_dir . '/server-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -123,14 +122,12 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
 		rmtree($backup_path);
-		rmtree($extract_path);
 	}
 }
 
diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index b62faeb5acf..5b0e76ee69d 100644
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -32,7 +32,6 @@ print $jf $junk_data;
 close $jf;
 
 my $backup_path = $primary->backup_dir . '/client-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -137,13 +136,11 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
-		rmtree($extract_path);
 		rmtree($backup_path);
 	}
 }
-- 
2.47.1

From 6e0f330b88eb027c36b1272b0bb7eccb1c50e39a Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 24 Jun 2025 11:33:20 +0530
Subject: [PATCH v10 1/8] Refactor: pg_waldump: Move some declarations to new
 pg_waldump.h

This change prepares for a second source file in this directory to
support reading WAL from tar files. Common structures, declarations,
and functions are being exported through this include file so
they can be used in both files.
---
 src/bin/pg_waldump/pg_waldump.c | 12 +++---------
 src/bin/pg_waldump/pg_waldump.h | 27 +++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 9 deletions(-)
 create mode 100644 src/bin/pg_waldump/pg_waldump.h

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index aae655966ef..0a0e9b7caaf 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -29,6 +29,7 @@
 #include "common/logging.h"
 #include "common/relpath.h"
 #include "getopt_long.h"
+#include "pg_waldump.h"
 #include "rmgrdesc.h"
 #include "storage/bufpage.h"
 
@@ -37,21 +38,14 @@
  * give a thought about doing the same in pg_walinspect contrib module as well.
  */
 
+int			WalSegSz;
+
 static const char *progname;
 
-static int	WalSegSz;
 static volatile sig_atomic_t time_to_stop = false;
 
 static const RelFileLocator emptyRelFileLocator = {0, 0, 0};
 
-typedef struct XLogDumpPrivate
-{
-	TimeLineID	timeline;
-	XLogRecPtr	startptr;
-	XLogRecPtr	endptr;
-	bool		endptr_reached;
-} XLogDumpPrivate;
-
 typedef struct XLogDumpConfig
 {
 	/* display options */
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
new file mode 100644
index 00000000000..926d529f9d6
--- /dev/null
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -0,0 +1,27 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_waldump.h - decode and display WAL
+ *
+ * Copyright (c) 2025, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  src/bin/pg_waldump/pg_waldump.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_WALDUMP_H
+#define PG_WALDUMP_H
+
+#include "access/xlogdefs.h"
+
+extern int	WalSegSz;
+
+/* Contains the necessary information to drive WAL decoding */
+typedef struct XLogDumpPrivate
+{
+	TimeLineID	timeline;
+	XLogRecPtr	startptr;
+	XLogRecPtr	endptr;
+	bool		endptr_reached;
+} XLogDumpPrivate;
+
+#endif							/* end of PG_WALDUMP_H */
-- 
2.47.1

From cd4adf2105028a44527fe3fbbea65153de8d8a4c Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 26 Jun 2025 11:42:53 +0530
Subject: [PATCH v10 2/8] Refactor: pg_waldump: Separate logic used to
 calculate the required read size.

This refactoring prepares the codebase for an upcoming patch that will
support reading WAL from tar files. The logic for calculating the
required read size has been updated to handle both normal WAL files
and WAL files located inside a tar archive.
---
 src/bin/pg_waldump/pg_waldump.c | 46 +++++++++++++++++++++++----------
 1 file changed, 33 insertions(+), 13 deletions(-)

diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 0a0e9b7caaf..a33fc28b9d5 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -327,6 +327,35 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
+/*
+ * Returns the size in bytes of the data to be read. Returns -1 if the end
+ * point has already been reached.
+ */
+static inline int
+required_read_len(XLogDumpPrivate *private, XLogRecPtr targetPagePtr,
+				  int reqLen)
+{
+	int			count = XLOG_BLCKSZ;
+
+	if (unlikely(private->endptr_reached))
+		return -1;
+
+	if (XLogRecPtrIsValid(private->endptr))
+	{
+		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
+			count = XLOG_BLCKSZ;
+		else if (targetPagePtr + reqLen <= private->endptr)
+			count = private->endptr - targetPagePtr;
+		else
+		{
+			private->endptr_reached = true;
+			return -1;
+		}
+	}
+
+	return count;
+}
+
 /* pg_waldump's XLogReaderRoutine->segment_open callback */
 static void
 WALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
@@ -384,21 +413,12 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
-	int			count = XLOG_BLCKSZ;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
 	WALReadError errinfo;
 
-	if (XLogRecPtrIsValid(private->endptr))
-	{
-		if (targetPagePtr + XLOG_BLCKSZ <= private->endptr)
-			count = XLOG_BLCKSZ;
-		else if (targetPagePtr + reqLen <= private->endptr)
-			count = private->endptr - targetPagePtr;
-		else
-		{
-			private->endptr_reached = true;
-			return -1;
-		}
-	}
+	/* Bail out if the count to be read is not valid */
+	if (count < 0)
+		return -1;
 
 	if (!WALRead(state, readBuff, targetPagePtr, count, private->timeline,
 				 &errinfo))
-- 
2.47.1

From f911d0ff34bc2c2e12fb0849785d2b5864c73594 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 25 Nov 2025 16:12:11 +0530
Subject: [PATCH v10 3/8] Refactor: pg_waldump: Restructure TAP tests.

Restructured some tests to run inside a loop, facilitating their
re-execution for decoding WAL from tar archives.

== NOTE ==
  This is not intended to be committed separately. It can be merged
  with the next patch, which is the main patch implementing this
  feature.
---
 src/bin/pg_waldump/t/001_basic.pl | 123 ++++++++++++++++--------------
 1 file changed, 67 insertions(+), 56 deletions(-)

diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 5db5d20136f..3288fadcf48 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -198,28 +198,6 @@ command_like(
 	],
 	qr/./,
 	'runs with start and end segment specified');
-command_fails_like(
-	[ 'pg_waldump', '--path' => $node->data_dir ],
-	qr/error: no start WAL location given/,
-	'path option requires start location');
-command_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-		'--end' => $end_lsn,
-	],
-	qr/./,
-	'runs with path option and start and end locations');
-command_fails_like(
-	[
-		'pg_waldump',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn,
-	],
-	qr/error: error in WAL record at/,
-	'falling off the end of the WAL results in an error');
-
 command_like(
 	[
 		'pg_waldump', '--quiet',
@@ -227,15 +205,6 @@ command_like(
 	],
 	qr/^$/,
 	'no output with --quiet option');
-command_fails_like(
-	[
-		'pg_waldump', '--quiet',
-		'--path' => $node->data_dir,
-		'--start' => $start_lsn
-	],
-	qr/error: error in WAL record at/,
-	'errors are shown with --quiet');
-
 
 # Test for: Display a message that we're skipping data if `from`
 # wasn't a pointer to the start of a record.
@@ -272,7 +241,6 @@ sub test_pg_waldump
 
 	my $result = IPC::Run::run [
 		'pg_waldump',
-		'--path' => $node->data_dir,
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
 		@opts
@@ -288,38 +256,81 @@ sub test_pg_waldump
 
 my @lines;
 
-@lines = test_pg_waldump;
-is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
+my @scenarios = (
+	{
+		'path' => $node->data_dir
+	});
 
-@lines = test_pg_waldump('--limit' => 6);
-is(@lines, 6, 'limit option observed');
+for my $scenario (@scenarios)
+{
+	my $path = $scenario->{'path'};
 
-@lines = test_pg_waldump('--fullpage');
-is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
+	SKIP:
+	{
+		command_fails_like(
+			[ 'pg_waldump', '--path' => $path ],
+			qr/error: no start WAL location given/,
+			'path option requires start location');
+		command_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+				'--end' => $end_lsn,
+			],
+			qr/./,
+			'runs with path option and start and end locations');
+		command_fails_like(
+			[
+				'pg_waldump',
+				'--path' => $path,
+				'--start' => $start_lsn,
+			],
+			qr/error: error in WAL record at/,
+			'falling off the end of the WAL results in an error');
 
-@lines = test_pg_waldump('--stats');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		command_fails_like(
+			[
+				'pg_waldump', '--quiet',
+				'--path' => $path,
+				'--start' => $start_lsn
+			],
+			qr/error: error in WAL record at/,
+			'errors are shown with --quiet');
 
-@lines = test_pg_waldump('--stats=record');
-like($lines[0], qr/WAL statistics/, "statistics on stdout");
-is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
+		@lines = test_pg_waldump('--path' => $path);
+		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-@lines = test_pg_waldump('--rmgr' => 'Btree');
-is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		is(@lines, 6, 'limit option observed');
 
-@lines = test_pg_waldump('--fork' => 'init');
-is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
-is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
-	0, 'only lines for selected relation');
+		@lines = test_pg_waldump('--path' => $path, '--stats');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-@lines = test_pg_waldump(
-	'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
-	'--block' => 1);
-is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		like($lines[0], qr/WAL statistics/, "statistics on stdout");
+		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
+		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
+
+		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
+		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
+			0, 'only lines for selected relation');
+
+		@lines = test_pg_waldump('--path' => $path,
+			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
+			'--block' => 1);
+		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+	}
+}
 
 done_testing();
-- 
2.47.1

From b8fba73c2abf78fd6972ac077b3d22332a4d477b Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Fri, 2 Jan 2026 17:07:34 +0530
Subject: [PATCH v10 4/8] pg_waldump: Add support for archived WAL decoding.

pg_waldump can now accept the path to a tar archive containing WAL
files and decode them. This feature was added primarily for
pg_verifybackup, which previously disabled WAL parsing for
tar-formatted backups.

Note that this patch requires that the WAL files within the archive be
in sequential order; an error will be reported otherwise. The next
patch is planned to remove this restriction.
---
 doc/src/sgml/ref/pg_waldump.sgml     |   8 +-
 src/bin/pg_waldump/Makefile          |   7 +-
 src/bin/pg_waldump/archive_waldump.c | 594 +++++++++++++++++++++++++++
 src/bin/pg_waldump/meson.build       |   4 +-
 src/bin/pg_waldump/pg_waldump.c      | 218 +++++++---
 src/bin/pg_waldump/pg_waldump.h      |  34 ++
 src/bin/pg_waldump/t/001_basic.pl    |  84 +++-
 src/tools/pgindent/typedefs.list     |   3 +
 8 files changed, 876 insertions(+), 76 deletions(-)
 create mode 100644 src/bin/pg_waldump/archive_waldump.c

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index ce23add5577..d004bb0f67e 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -141,13 +141,17 @@ PostgreSQL documentation
       <term><option>--path=<replaceable>path</replaceable></option></term>
       <listitem>
        <para>
-        Specifies a directory to search for WAL segment files or a
-        directory with a <literal>pg_wal</literal> subdirectory that
+        Specifies a tar archive or a directory to search for WAL segment files
+        or a directory with a <literal>pg_wal</literal> subdirectory that
         contains such files.  The default is to search in the current
         directory, the <literal>pg_wal</literal> subdirectory of the
         current directory, and the <literal>pg_wal</literal> subdirectory
         of <envar>PGDATA</envar>.
        </para>
+       <para>
+        If a tar archive is provided, its WAL segment files must be in
+        sequential order; otherwise, an error will be reported.
+       </para>
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index 4c1ee649501..aabb87566a2 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -3,6 +3,9 @@
 PGFILEDESC = "pg_waldump - decode and display WAL"
 PGAPPICON=win32
 
+# make these available to TAP test scripts
+export TAR
+
 subdir = src/bin/pg_waldump
 top_builddir = ../../..
 include $(top_builddir)/src/Makefile.global
@@ -10,13 +13,15 @@ include $(top_builddir)/src/Makefile.global
 OBJS = \
 	$(RMGRDESCOBJS) \
 	$(WIN32RES) \
+	archive_waldump.o \
 	compat.o \
 	pg_waldump.o \
 	rmgrdesc.o \
 	xlogreader.o \
 	xlogstats.o
 
-override CPPFLAGS := -DFRONTEND $(CPPFLAGS)
+override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
new file mode 100644
index 00000000000..6ba067163d5
--- /dev/null
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -0,0 +1,594 @@
+/*-------------------------------------------------------------------------
+ *
+ * archive_waldump.c
+ *		A generic facility for reading WAL data from tar archives via archive
+ *		streamer.
+ *
+ * Portions Copyright (c) 2026, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		src/bin/pg_waldump/archive_waldump.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres_fe.h"
+
+#include <unistd.h>
+
+#include "access/xlog_internal.h"
+#include "common/hashfn.h"
+#include "common/logging.h"
+#include "fe_utils/simple_list.h"
+#include "pg_waldump.h"
+
+/*
+ * How many bytes should we try to read from a file at once?
+ */
+#define READ_CHUNK_SIZE				(128 * 1024)
+
+/* Hash entry structure for holding WAL segment data read from the archive */
+typedef struct ArchivedWALEntry
+{
+	uint32		status;			/* hash status */
+	XLogSegNo	segno;			/* hash key: WAL segment number */
+	TimeLineID	timeline;		/* timeline of this wal file */
+
+	StringInfoData buf;
+	bool		tmpseg_exists;	/* spill file exists? */
+
+	int			total_read;		/* total read of archived WAL segment */
+} ArchivedWALEntry;
+
+#define SH_PREFIX				ArchivedWAL
+#define SH_ELEMENT_TYPE			ArchivedWALEntry
+#define SH_KEY_TYPE				XLogSegNo
+#define SH_KEY					segno
+#define SH_HASH_KEY(tb, key)	murmurhash64((uint64) key)
+#define SH_EQUAL(tb, a, b)		(a == b)
+#define SH_GET_HASH(tb, a)		a->hash
+#define SH_SCOPE				static inline
+#define SH_RAW_ALLOCATOR		pg_malloc0
+#define SH_DECLARE
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
+static ArchivedWAL_hash *ArchivedWAL_HTAB = NULL;
+
+typedef struct astreamer_waldump
+{
+	astreamer	base;
+	XLogDumpPrivate *privateInfo;
+} astreamer_waldump;
+
+static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
+static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
+											   XLogDumpPrivate *privateInfo);
+
+static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
+static void astreamer_waldump_content(astreamer *streamer,
+									  astreamer_member *member,
+									  const char *data, int len,
+									  astreamer_archive_context context);
+static void astreamer_waldump_finalize(astreamer *streamer);
+static void astreamer_waldump_free(astreamer *streamer);
+
+static bool member_is_wal_file(astreamer_waldump *mystreamer,
+							   astreamer_member *member,
+							   XLogSegNo *curSegNo,
+							   TimeLineID *curTimeline);
+
+static const astreamer_ops astreamer_waldump_ops = {
+	.content = astreamer_waldump_content,
+	.finalize = astreamer_waldump_finalize,
+	.free = astreamer_waldump_free
+};
+
+/*
+ * Returns true if the given file is a tar archive and outputs its compression
+ * algorithm.
+ */
+bool
+is_archive_file(const char *fname, pg_compress_algorithm *compression)
+{
+	int			fname_len = strlen(fname);
+	pg_compress_algorithm compress_algo;
+
+	/* Now, check the compression type of the tar */
+	if (fname_len > 4 &&
+		strcmp(fname + fname_len - 4, ".tar") == 0)
+		compress_algo = PG_COMPRESSION_NONE;
+	else if (fname_len > 4 &&
+			 strcmp(fname + fname_len - 4, ".tgz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 7 &&
+			 strcmp(fname + fname_len - 7, ".tar.gz") == 0)
+		compress_algo = PG_COMPRESSION_GZIP;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.lz4") == 0)
+		compress_algo = PG_COMPRESSION_LZ4;
+	else if (fname_len > 8 &&
+			 strcmp(fname + fname_len - 8, ".tar.zst") == 0)
+		compress_algo = PG_COMPRESSION_ZSTD;
+	else
+		return false;
+
+	*compression = compress_algo;
+
+	return true;
+}
+
+/*
+ * Initializes the tar archive reader, creates a hash table for WAL entries,
+ * checks for existing valid WAL segments in the archive file and retrieves the
+ * segment size, and sets up filters for relevant entries.
+ */
+void
+init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
+					pg_compress_algorithm compression)
+{
+	int			fd;
+	astreamer  *streamer;
+	ArchivedWALEntry *entry = NULL;
+	XLogLongPageHeader longhdr;
+
+	/* Open tar archive and store its file descriptor */
+	fd = open_file_in_directory(waldir, privateInfo->archive_name);
+
+	if (fd < 0)
+		pg_fatal("could not open file \"%s\"", privateInfo->archive_name);
+
+	privateInfo->archive_fd = fd;
+
+	streamer = astreamer_waldump_new(privateInfo);
+
+	/* Before that we must parse the tar archive. */
+	streamer = astreamer_tar_parser_new(streamer);
+
+	/* Before that we must decompress, if archive is compressed. */
+	if (compression == PG_COMPRESSION_GZIP)
+		streamer = astreamer_gzip_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_LZ4)
+		streamer = astreamer_lz4_decompressor_new(streamer);
+	else if (compression == PG_COMPRESSION_ZSTD)
+		streamer = astreamer_zstd_decompressor_new(streamer);
+
+	privateInfo->archive_streamer = streamer;
+
+	/* Hash table storing WAL entries read from the archive */
+	ArchivedWAL_HTAB = ArchivedWAL_create(16, NULL);
+
+	/*
+	 * Verify that the archive contains valid WAL files and fetch WAL segment
+	 * size
+	 */
+	while (entry == NULL || entry->buf.len < XLOG_BLCKSZ)
+	{
+		if (read_archive_file(privateInfo, XLOG_BLCKSZ) == 0)
+			pg_fatal("could not find WAL in \"%s\" archive",
+					 privateInfo->archive_name);
+
+		entry = privateInfo->cur_wal;
+	}
+
+	/* Set WalSegSz if WAL data is successfully read */
+	longhdr = (XLogLongPageHeader) entry->buf.data;
+
+	WalSegSz = longhdr->xlp_seg_size;
+
+	if (!IsValidWalSegSize(WalSegSz))
+	{
+		pg_log_error(ngettext("invalid WAL segment size in WAL file from archive \"%s\" (%d byte)",
+							  "invalid WAL segment size in WAL file from archive \"%s\" (%d bytes)",
+							  WalSegSz),
+					 privateInfo->archive_name, WalSegSz);
+		pg_log_error_detail("The WAL segment size must be a power of two between 1 MB and 1 GB.");
+		exit(1);
+	}
+
+	/*
+	 * With the WAL segment size available, we can now initialize the
+	 * dependent start and end segment numbers.
+	 */
+	Assert(!XLogRecPtrIsInvalid(privateInfo->startptr));
+	XLByteToSeg(privateInfo->startptr, privateInfo->startSegNo, WalSegSz);
+
+	if (XLogRecPtrIsInvalid(privateInfo->endptr))
+		privateInfo->endSegNo = UINT64_MAX;
+	else
+		XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+}
+
+/*
+ * Release the archive streamer chain and close the archive file.
+ */
+void
+free_archive_reader(XLogDumpPrivate *privateInfo)
+{
+	/*
+	 * NB: Normally, astreamer_finalize() is called before astreamer_free() to
+	 * flush any remaining buffered data or to ensure the end of the tar
+	 * archive is reached. However, when decoding a WAL file, once we hit the
+	 * end LSN, any remaining WAL data in the buffer or the tar archive's
+	 * unreached end can be safely ignored.
+	 */
+	astreamer_free(privateInfo->archive_streamer);
+
+	/* Close the file. */
+	if (close(privateInfo->archive_fd) != 0)
+		pg_log_error("could not close file \"%s\": %m",
+					 privateInfo->archive_name);
+}
+
+/*
+ * Copies WAL data from astreamer to readBuff; if unavailable, fetches more
+ * from the tar archive via astreamer.
+ */
+int
+read_archive_wal_page(XLogDumpPrivate *privateInfo, XLogRecPtr targetPagePtr,
+					  Size count, char *readBuff)
+{
+	char	   *p = readBuff;
+	Size		nbytes = count;
+	XLogRecPtr	recptr = targetPagePtr;
+	XLogSegNo	segno;
+	ArchivedWALEntry *entry;
+
+	XLByteToSeg(targetPagePtr, segno, WalSegSz);
+	entry = get_archive_wal_entry(segno, privateInfo);
+
+	while (nbytes > 0)
+	{
+		char	   *buf = entry->buf.data;
+		int			len = entry->buf.len;
+
+		/* WAL record range that the buffer contains */
+		XLogRecPtr	endPtr;
+		XLogRecPtr	startPtr;
+
+		XLogSegNoOffsetToRecPtr(entry->segno, entry->total_read,
+								WalSegSz, endPtr);
+		startPtr = endPtr - len;
+
+		/*
+		 * pg_waldump may request to re-read the currently active page, but
+		 * never a page older than the current one. Therefore, any fully
+		 * consumed WAL data preceding the current page can be safely
+		 * discarded.
+		 */
+		if (recptr >= endPtr)
+		{
+			/* Discard the buffered data */
+			resetStringInfo(&entry->buf);
+			len = 0;
+
+			/*
+			 * Push back the partial page data for the current page to the
+			 * buffer, ensuring it remains full page available for re-reading
+			 * if requested.
+			 */
+			if (p > readBuff)
+			{
+				Assert((count - nbytes) > 0);
+				appendBinaryStringInfo(&entry->buf, readBuff, count - nbytes);
+			}
+		}
+
+		if (len > 0 && recptr > startPtr)
+		{
+			int			skipBytes = 0;
+
+			/*
+			 * The required offset is not at the start of the buffer, so skip
+			 * bytes until reaching the desired offset of the target page.
+			 */
+			skipBytes = recptr - startPtr;
+
+			buf += skipBytes;
+			len -= skipBytes;
+		}
+
+		if (len > 0)
+		{
+			int			readBytes = len >= nbytes ? nbytes : len;
+
+			/* Ensure the reading page is in the buffer */
+			Assert(recptr >= startPtr && recptr < endPtr);
+
+			memcpy(p, buf, readBytes);
+
+			/* Update state for read */
+			nbytes -= readBytes;
+			p += readBytes;
+			recptr += readBytes;
+		}
+		else
+		{
+			/*
+			 * Fetch more data; raise an error if it's not the current segment
+			 * being read by the archive streamer or if reading of the
+			 * archived file has finished.
+			 */
+			if (privateInfo->cur_wal != entry ||
+				read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+			{
+				char		fname[MAXFNAMELEN];
+
+				XLogFileName(fname, privateInfo->timeline, entry->segno,
+							 WalSegSz);
+				pg_fatal("could not read file \"%s\" from archive \"%s\": read %lld of %lld",
+						 fname, privateInfo->archive_name,
+						 (long long int) count - nbytes,
+						 (long long int) nbytes);
+			}
+		}
+	}
+
+	/*
+	 * Should have either have successfully read all the requested bytes or
+	 * reported a failure before this point.
+	 */
+	Assert(nbytes == 0);
+
+	/*
+	 * NB: We return the fixed value provided as input. Although we could
+	 * return a boolean since we either successfully read the WAL page or
+	 * raise an error, but the caller expects this value to be returned. The
+	 * routine that reads WAL pages from the physical WAL file follows the
+	 * same convention.
+	 */
+	return count;
+}
+
+/*
+ * Reads the archive file and passes it to the archive streamer for
+ * decompression.
+ */
+static int
+read_archive_file(XLogDumpPrivate *privateInfo, Size count)
+{
+	int			rc;
+	char	   *buffer;
+
+	buffer = pg_malloc(READ_CHUNK_SIZE * sizeof(uint8));
+
+	rc = read(privateInfo->archive_fd, buffer, count);
+	if (rc < 0)
+		pg_fatal("could not read file \"%s\": %m",
+				 privateInfo->archive_name);
+
+	/*
+	 * Decompress (if required), and then parse the previously read contents
+	 * of the tar file.
+	 */
+	if (rc > 0)
+		astreamer_content(privateInfo->archive_streamer, NULL,
+						  buffer, rc, ASTREAMER_UNKNOWN);
+	pg_free(buffer);
+
+	return rc;
+}
+
+/*
+ * Returns the archived WAL entry from the hash table if it exists. Otherwise,
+ * it invokes the routine to read the archived file, which then populates the
+ * entry in the hash table.
+ */
+static ArchivedWALEntry *
+get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
+{
+	ArchivedWALEntry *entry = NULL;
+	char		fname[MAXFNAMELEN];
+
+	/* Search hash table */
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry != NULL)
+		return entry;
+
+	/* Needed WAL yet to be decoded from archive, do the same */
+	while (1)
+	{
+		entry = privateInfo->cur_wal;
+
+		/* Fetch more data */
+		if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+			break;			/* archive file ended */
+
+		/*
+		 * Either, here for the first time, or the archived streamer is
+		 * reading a non-WAL file or an irrelevant WAL file.
+		 */
+		if (entry == NULL)
+			continue;
+
+		/* Found the required entry */
+		if (entry->segno == segno)
+			return entry;
+
+		/*
+		 * Ignore if the timeline is different or the current segment is not
+		 * the desired one.
+		 */
+		if (privateInfo->timeline != entry->timeline ||
+			privateInfo->startSegNo > entry->segno ||
+			privateInfo->endSegNo < entry->segno)
+		{
+			privateInfo->cur_wal = NULL;
+			continue;
+		}
+
+		/*
+		 * XXX: If the segment being read not the requested one, the data must
+		 * be buffered, as we currently lack the mechanism to write it to a
+		 * temporary file. This is a known limitation that will be fixed in the
+		 * next patch, as the buffer could grow up to the full WAL segment
+		 * size.
+		 */
+		if (segno > entry->segno)
+			continue;
+
+		/* WAL segments must be archived in order */
+		pg_log_error("WAL files are not archived in sequential order");
+		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
+							segno, entry->segno);
+		exit(1);
+	}
+
+	/* Requested WAL segment not found */
+	XLogFileName(fname, privateInfo->timeline, segno, WalSegSz);
+	pg_fatal("could not find file \"%s\" in archive", fname);
+}
+
+/*
+ * Create an astreamer that can read WAL from a tar file.
+ */
+static astreamer *
+astreamer_waldump_new(XLogDumpPrivate *privateInfo)
+{
+	astreamer_waldump *streamer;
+
+	streamer = palloc0(sizeof(astreamer_waldump));
+	*((const astreamer_ops **) &streamer->base.bbs_ops) =
+		&astreamer_waldump_ops;
+
+	streamer->privateInfo = privateInfo;
+
+	return &streamer->base;
+}
+
+/*
+ * Main entry point of the archive streamer for reading WAL data from a tar
+ * file. If a member is identified as a valid WAL file, a hash entry is created
+ * for it, and its contents are copied into that entry's buffer, making them
+ * accessible to the decoding routine.
+ */
+static void
+astreamer_waldump_content(astreamer *streamer, astreamer_member *member,
+						  const char *data, int len,
+						  astreamer_archive_context context)
+{
+	astreamer_waldump *mystreamer = (astreamer_waldump *) streamer;
+	XLogDumpPrivate *privateInfo = mystreamer->privateInfo;
+
+	Assert(context != ASTREAMER_UNKNOWN);
+
+	switch (context)
+	{
+		case ASTREAMER_MEMBER_HEADER:
+			{
+				XLogSegNo	segno;
+				TimeLineID	timeline;
+				ArchivedWALEntry *entry;
+				bool		found;
+
+				pg_log_debug("reading \"%s\"", member->pathname);
+
+				if (!member_is_wal_file(mystreamer, member,
+										&segno, &timeline))
+					break;
+
+				entry = ArchivedWAL_insert(ArchivedWAL_HTAB, segno, &found);
+
+				/*
+				 * Shouldn't happen, but if it does, simply ignore the
+				 * duplicate WAL file.
+				 */
+				if (found)
+				{
+					pg_log_warning("ignoring duplicate WAL file found in archive: \"%s\"",
+								   member->pathname);
+					break;
+				}
+
+				initStringInfo(&entry->buf);
+				entry->timeline = timeline;
+				entry->total_read = 0;
+
+				privateInfo->cur_wal = entry;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_CONTENTS:
+			if (privateInfo->cur_wal)
+			{
+				appendBinaryStringInfo(&privateInfo->cur_wal->buf, data, len);
+				privateInfo->cur_wal->total_read += len;
+			}
+			break;
+
+		case ASTREAMER_MEMBER_TRAILER:
+			privateInfo->cur_wal = NULL;
+			break;
+
+		case ASTREAMER_ARCHIVE_TRAILER:
+			break;
+
+		default:
+			/* Shouldn't happen. */
+			pg_fatal("unexpected state while parsing tar file");
+	}
+}
+
+/*
+ * End-of-stream processing for an astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_finalize(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+}
+
+/*
+ * Free memory associated with a astreamer_waldump stream.
+ */
+static void
+astreamer_waldump_free(astreamer *streamer)
+{
+	Assert(streamer->bbs_next == NULL);
+	pfree(streamer);
+}
+
+/*
+ * Returns true if the archive member name matches the WAL naming format. If
+ * successful, it also outputs the WAL segment number, and timeline.
+ */
+static bool
+member_is_wal_file(astreamer_waldump *mystreamer, astreamer_member *member,
+				   XLogSegNo *curSegNo, TimeLineID *curTimeline)
+{
+	int			pathlen;
+	XLogSegNo	segNo;
+	TimeLineID	timeline;
+	char	   *fname;
+
+	/* We are only interested in normal files. */
+	if (member->is_directory || member->is_link)
+		return false;
+
+	pathlen = strlen(member->pathname);
+	if (pathlen < XLOG_FNAME_LEN)
+		return false;
+
+	/* WAL file could be with full path */
+	fname = member->pathname + (pathlen - XLOG_FNAME_LEN);
+	if (!IsXLogFileName(fname))
+		return false;
+
+	/*
+	 * XXX: On some systems (e.g., OpenBSD), the tar utility includes
+	 * PaxHeaders when creating an archive. These are special entries that
+	 * store extended metadata for the file entry immediately following them,
+	 * and they share the exact same name as that file.
+	 */
+	if (strstr(member->pathname, "PaxHeaders."))
+		return false;
+
+	/* Parse position from file */
+	XLogFromFileName(fname, &timeline, &segNo, WalSegSz);
+
+	*curSegNo = segNo;
+	*curTimeline = timeline;
+
+	return true;
+}
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 633a9874bb5..a93bd947ca2 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -1,6 +1,7 @@
 # Copyright (c) 2022-2026, PostgreSQL Global Development Group
 
 pg_waldump_sources = files(
+  'archive_waldump.c',
   'compat.c',
   'pg_waldump.c',
   'rmgrdesc.c',
@@ -18,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, lz4, zstd],
+  dependencies: [frontend_code, lz4, zstd, libpq],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
@@ -29,6 +30,7 @@ tests += {
   'sd': meson.current_source_dir(),
   'bd': meson.current_build_dir(),
   'tap': {
+    'env': {'TAR': tar.found() ? tar.full_path() : ''},
     'tests': [
       't/001_basic.pl',
       't/002_save_fullpage.pl',
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index a33fc28b9d5..e2c96c3f4ca 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -38,7 +38,7 @@
  * give a thought about doing the same in pg_walinspect contrib module as well.
  */
 
-int			WalSegSz;
+int			WalSegSz = DEFAULT_XLOG_SEG_SIZE;
 
 static const char *progname;
 
@@ -178,7 +178,7 @@ split_path(const char *path, char **dir, char **fname)
  *
  * return a read only fd
  */
-static int
+int
 open_file_in_directory(const char *directory, const char *fname)
 {
 	int			fd = -1;
@@ -444,6 +444,45 @@ WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 	return count;
 }
 
+/*
+ * pg_waldump's XLogReaderRoutine->segment_open callback to support dumping WAL
+ * files from tar archives.
+ */
+static void
+TarWALDumpOpenSegment(XLogReaderState *state, XLogSegNo nextSegNo,
+					  TimeLineID *tli_p)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->segment_close callback.
+ */
+static void
+TarWALDumpCloseSegment(XLogReaderState *state)
+{
+	/* No action needed */
+}
+
+/*
+ * pg_waldump's XLogReaderRoutine->page_read callback to support dumping WAL
+ * files from tar archives.
+ */
+static int
+TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				   XLogRecPtr targetPtr, char *readBuff)
+{
+	XLogDumpPrivate *private = state->private_data;
+	int			count = required_read_len(private, targetPagePtr, reqLen);
+
+	/* Bail out if the count to be read is not valid */
+	if (count < 0)
+		return -1;
+
+	/* Read the WAL page from the archive streamer */
+	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
+}
+
 /*
  * Boolean to return whether the given WAL record matches a specific relation
  * and optionally block.
@@ -781,8 +820,8 @@ usage(void)
 	printf(_("  -F, --fork=FORK        only show records that modify blocks in fork FORK;\n"
 			 "                         valid names are main, fsm, vm, init\n"));
 	printf(_("  -n, --limit=N          number of records to display\n"));
-	printf(_("  -p, --path=PATH        directory in which to find WAL segment files or a\n"
-			 "                         directory with a ./pg_wal that contains such files\n"
+	printf(_("  -p, --path=PATH        tar archive or a directory in which to find WAL segment files or\n"
+			 "                         a directory with a ./pg_wal that contains such files\n"
 			 "                         (default: current directory, ./pg_wal, $PGDATA/pg_wal)\n"));
 	printf(_("  -q, --quiet            do not print any output, except for errors\n"));
 	printf(_("  -r, --rmgr=RMGR        only show records generated by resource manager RMGR;\n"
@@ -814,7 +853,10 @@ main(int argc, char **argv)
 	XLogRecord *record;
 	XLogRecPtr	first_record;
 	char	   *waldir = NULL;
+	char	   *walpath = NULL;
 	char	   *errormsg;
+	bool		is_archive = false;
+	pg_compress_algorithm compression;
 
 	static struct option long_options[] = {
 		{"bkp-details", no_argument, NULL, 'b'},
@@ -946,7 +988,7 @@ main(int argc, char **argv)
 				}
 				break;
 			case 'p':
-				waldir = pg_strdup(optarg);
+				walpath = pg_strdup(optarg);
 				break;
 			case 'q':
 				config.quiet = true;
@@ -1110,10 +1152,20 @@ main(int argc, char **argv)
 		goto bad_argument;
 	}
 
-	if (waldir != NULL)
+	if (walpath != NULL)
 	{
+		/* validate path points to tar archive */
+		if (is_archive_file(walpath, &compression))
+		{
+			char	   *fname = NULL;
+
+			split_path(walpath, &waldir, &fname);
+
+			private.archive_name = fname;
+			is_archive = true;
+		}
 		/* validate path points to directory */
-		if (!verify_directory(waldir))
+		else if (!verify_directory(walpath))
 		{
 			pg_log_error("could not open directory \"%s\": %m", waldir);
 			goto bad_argument;
@@ -1131,6 +1183,17 @@ main(int argc, char **argv)
 		int			fd;
 		XLogSegNo	segno;
 
+		/*
+		 * If a tar archive is passed using the --path option, all other
+		 * arguments become unnecessary.
+		 */
+		if (is_archive)
+		{
+			pg_log_error("unnecessary command-line arguments specified with tar archive (first is \"%s\")",
+						 argv[optind]);
+			goto bad_argument;
+		}
+
 		split_path(argv[optind], &directory, &fname);
 
 		if (waldir == NULL && directory != NULL)
@@ -1141,69 +1204,77 @@ main(int argc, char **argv)
 				pg_fatal("could not open directory \"%s\": %m", waldir);
 		}
 
-		waldir = identify_target_directory(waldir, fname);
-		fd = open_file_in_directory(waldir, fname);
-		if (fd < 0)
-			pg_fatal("could not open file \"%s\"", fname);
-		close(fd);
-
-		/* parse position from file */
-		XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
-
-		if (!XLogRecPtrIsValid(private.startptr))
-			XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
-		else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+		if (fname != NULL && is_archive_file(fname, &compression))
 		{
-			pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.startptr),
-						 fname);
-			goto bad_argument;
+			private.archive_name = fname;
+			is_archive = true;
 		}
-
-		/* no second file specified, set end position */
-		if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
-			XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
-
-		/* parse ENDSEG if passed */
-		if (optind + 1 < argc)
+		else
 		{
-			XLogSegNo	endsegno;
-
-			/* ignore directory, already have that */
-			split_path(argv[optind + 1], &directory, &fname);
-
+			waldir = identify_target_directory(waldir, fname);
 			fd = open_file_in_directory(waldir, fname);
 			if (fd < 0)
 				pg_fatal("could not open file \"%s\"", fname);
 			close(fd);
 
 			/* parse position from file */
-			XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+			XLogFromFileName(fname, &private.timeline, &segno, WalSegSz);
 
-			if (endsegno < segno)
-				pg_fatal("ENDSEG %s is before STARTSEG %s",
-						 argv[optind + 1], argv[optind]);
+			if (!XLogRecPtrIsValid(private.startptr))
+				XLogSegNoOffsetToRecPtr(segno, 0, WalSegSz, private.startptr);
+			else if (!XLByteInSeg(private.startptr, segno, WalSegSz))
+			{
+				pg_log_error("start WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.startptr),
+							 fname);
+				goto bad_argument;
+			}
 
-			if (!XLogRecPtrIsValid(private.endptr))
-				XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
-										private.endptr);
+			/* no second file specified, set end position */
+			if (!(optind + 1 < argc) && !XLogRecPtrIsValid(private.endptr))
+				XLogSegNoOffsetToRecPtr(segno + 1, 0, WalSegSz, private.endptr);
 
-			/* set segno to endsegno for check of --end */
-			segno = endsegno;
-		}
+			/* parse ENDSEG if passed */
+			if (optind + 1 < argc)
+			{
+				XLogSegNo	endsegno;
 
+				/* ignore directory, already have that */
+				split_path(argv[optind + 1], &directory, &fname);
 
-		if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
-			private.endptr != (segno + 1) * WalSegSz)
-		{
-			pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
-						 LSN_FORMAT_ARGS(private.endptr),
-						 argv[argc - 1]);
-			goto bad_argument;
+				fd = open_file_in_directory(waldir, fname);
+				if (fd < 0)
+					pg_fatal("could not open file \"%s\"", fname);
+				close(fd);
+
+				/* parse position from file */
+				XLogFromFileName(fname, &private.timeline, &endsegno, WalSegSz);
+
+				if (endsegno < segno)
+					pg_fatal("ENDSEG %s is before STARTSEG %s",
+							 argv[optind + 1], argv[optind]);
+
+				if (!XLogRecPtrIsValid(private.endptr))
+					XLogSegNoOffsetToRecPtr(endsegno + 1, 0, WalSegSz,
+											private.endptr);
+
+				/* set segno to endsegno for check of --end */
+				segno = endsegno;
+			}
+
+
+			if (!XLByteInSeg(private.endptr, segno, WalSegSz) &&
+				private.endptr != (segno + 1) * WalSegSz)
+			{
+				pg_log_error("end WAL location %X/%08X is not inside file \"%s\"",
+							 LSN_FORMAT_ARGS(private.endptr),
+							 argv[argc - 1]);
+				goto bad_argument;
+			}
 		}
 	}
-	else
-		waldir = identify_target_directory(waldir, NULL);
+	else if (!is_archive)
+		waldir = identify_target_directory(walpath, NULL);
 
 	/* we don't know what to print */
 	if (!XLogRecPtrIsValid(private.startptr))
@@ -1215,12 +1286,36 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
-	xlogreader_state =
-		XLogReaderAllocate(WalSegSz, waldir,
-						   XL_ROUTINE(.page_read = WALDumpReadPage,
-									  .segment_open = WALDumpOpenSegment,
-									  .segment_close = WALDumpCloseSegment),
-						   &private);
+	if (is_archive)
+	{
+		/*
+		 * A NULL WAL directory indicates that the archive file is located in
+		 * the current working directory of the pg_waldump execution
+		 */
+		waldir = waldir ? pg_strdup(waldir) : pg_strdup(".");
+
+		/* Set up for reading tar file */
+		init_archive_reader(&private, waldir, compression);
+
+		/* Routine to decode WAL files in tar archive */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = TarWALDumpReadPage,
+										  .segment_open = TarWALDumpOpenSegment,
+										  .segment_close = TarWALDumpCloseSegment),
+							   &private);
+	}
+	else
+	{
+		/* Routine to decode WAL files */
+		xlogreader_state =
+			XLogReaderAllocate(WalSegSz, waldir,
+							   XL_ROUTINE(.page_read = WALDumpReadPage,
+										  .segment_open = WALDumpOpenSegment,
+										  .segment_close = WALDumpCloseSegment),
+							   &private);
+	}
+
 	if (!xlogreader_state)
 		pg_fatal("out of memory while allocating a WAL reading processor");
 
@@ -1329,6 +1424,9 @@ main(int argc, char **argv)
 
 	XLogReaderFree(xlogreader_state);
 
+	if (is_archive)
+		free_archive_reader(&private);
+
 	return EXIT_SUCCESS;
 
 bad_argument:
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index 926d529f9d6..ec7a33d40e0 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -12,9 +12,13 @@
 #define PG_WALDUMP_H
 
 #include "access/xlogdefs.h"
+#include "fe_utils/astreamer.h"
 
 extern int	WalSegSz;
 
+/* Forward declaration */
+struct ArchivedWALEntry;
+
 /* Contains the necessary information to drive WAL decoding */
 typedef struct XLogDumpPrivate
 {
@@ -22,6 +26,36 @@ typedef struct XLogDumpPrivate
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	bool		endptr_reached;
+
+	/* Fields required to read WAL from archive */
+	char	   *archive_name;	/* Tar archive name */
+	int			archive_fd;		/* File descriptor for the open tar file */
+
+	astreamer  *archive_streamer;
+
+	/* What the archive streamer is currently reading */
+	struct ArchivedWALEntry *cur_wal;
+
+	/*
+	 * Although these values can be easily derived from startptr and endptr,
+	 * doing so repeatedly for each archived member would be inefficient, as
+	 * it would involve recalculating and filtering out irrelevant WAL
+	 * segments.
+	 */
+	XLogSegNo	startSegNo;
+	XLogSegNo	endSegNo;
 } XLogDumpPrivate;
 
+extern int	open_file_in_directory(const char *directory, const char *fname);
+
+extern bool is_archive_file(const char *fname,
+							pg_compress_algorithm *compression);
+extern void init_archive_reader(XLogDumpPrivate *privateInfo,
+								const char *waldir,
+								pg_compress_algorithm compression);
+extern void free_archive_reader(XLogDumpPrivate *privateInfo);
+extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
+								  XLogRecPtr targetPagePtr,
+								  Size count, char *readBuff);
+
 #endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 3288fadcf48..13567fbdba1 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -3,10 +3,13 @@
 
 use strict;
 use warnings FATAL => 'all';
+use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
 
+my $tar = $ENV{TAR};
+
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
 program_options_handling_ok('pg_waldump');
@@ -235,7 +238,7 @@ command_like(
 sub test_pg_waldump
 {
 	local $Test::Builder::Level = $Test::Builder::Level + 1;
-	my @opts = @_;
+	my ($path, @opts) = @_;
 
 	my ($stdout, $stderr);
 
@@ -243,6 +246,7 @@ sub test_pg_waldump
 		'pg_waldump',
 		'--start' => $start_lsn,
 		'--end' => $end_lsn,
+		'--path' => $path,
 		@opts
 	  ],
 	  '>' => \$stdout,
@@ -254,11 +258,50 @@ sub test_pg_waldump
 	return @lines;
 }
 
-my @lines;
+# Create a tar archive, sorting the file order
+sub generate_archive
+{
+	my ($archive, $directory, $compression_flags) = @_;
+
+	my @files;
+	opendir my $dh, $directory or die "opendir: $!";
+	while (my $entry = readdir $dh) {
+		# Skip '.' and '..'
+		next if $entry eq '.' || $entry eq '..';
+		push @files, $entry;
+	}
+	closedir $dh;
+
+	@files = sort @files;
+
+	# move into the WAL directory before archiving files
+	my $cwd = getcwd;
+	chdir($directory) || die "chdir: $!";
+	command_ok([$tar, $compression_flags, $archive, @files]);
+	chdir($cwd) || die "chdir: $!";
+}
+
+my $tmp_dir = PostgreSQL::Test::Utils::tempdir_short();
 
 my @scenarios = (
 	{
-		'path' => $node->data_dir
+		'path' => $node->data_dir,
+		'is_archive' => 0,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar",
+		'compression_method' => 'none',
+		'compression_flags' => '-cf',
+		'is_archive' => 1,
+		'enabled' => 1
+	},
+	{
+		'path' => "$tmp_dir/pg_wal.tar.gz",
+		'compression_method' => 'gzip',
+		'compression_flags' => '-czf',
+		'is_archive' => 1,
+		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
 	});
 
 for my $scenario (@scenarios)
@@ -267,6 +310,19 @@ for my $scenario (@scenarios)
 
 	SKIP:
 	{
+		skip "tar command is not available", 3
+		  if !defined $tar;
+		skip "$scenario->{'compression_method'} compression not supported by this build", 3
+		  if !$scenario->{'enabled'} && $scenario->{'is_archive'};
+
+		  # create pg_wal archive
+		  if ($scenario->{'is_archive'})
+		  {
+			  generate_archive($path,
+				  $node->data_dir . '/pg_wal',
+				  $scenario->{'compression_flags'});
+		  }
+
 		command_fails_like(
 			[ 'pg_waldump', '--path' => $path ],
 			qr/error: no start WAL location given/,
@@ -298,38 +354,42 @@ for my $scenario (@scenarios)
 			qr/error: error in WAL record at/,
 			'errors are shown with --quiet');
 
-		@lines = test_pg_waldump('--path' => $path);
+		my @lines;
+		@lines = test_pg_waldump($path);
 		is(grep(!/^rmgr: \w/, @lines), 0, 'all output lines are rmgr lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--limit' => 6);
+		@lines = test_pg_waldump($path, '--limit' => 6);
 		is(@lines, 6, 'limit option observed');
 
-		@lines = test_pg_waldump('--path' => $path, '--fullpage');
+		@lines = test_pg_waldump($path, '--fullpage');
 		is(grep(!/^rmgr:.*\bFPW\b/, @lines), 0, 'all output lines are FPW');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats');
+		@lines = test_pg_waldump($path, '--stats');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--stats=record');
+		@lines = test_pg_waldump($path, '--stats=record');
 		like($lines[0], qr/WAL statistics/, "statistics on stdout");
 		is(grep(/^rmgr:/, @lines), 0, 'no rmgr lines output');
 
-		@lines = test_pg_waldump('--path' => $path, '--rmgr' => 'Btree');
+		@lines = test_pg_waldump($path, '--rmgr' => 'Btree');
 		is(grep(!/^rmgr: Btree/, @lines), 0, 'only Btree lines');
 
-		@lines = test_pg_waldump('--path' => $path, '--fork' => 'init');
+		@lines = test_pg_waldump($path, '--fork' => 'init');
 		is(grep(!/fork init/, @lines), 0, 'only init fork lines');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_t1_oid");
 		is(grep(!/rel $default_ts_oid\/$postgres_db_oid\/$rel_t1_oid/, @lines),
 			0, 'only lines for selected relation');
 
-		@lines = test_pg_waldump('--path' => $path,
+		@lines = test_pg_waldump($path,
 			'--relation' => "$default_ts_oid/$postgres_db_oid/$rel_i1a_oid",
 			'--block' => 1);
 		is(grep(!/\bblk 1\b/, @lines), 0, 'only lines for selected block');
+
+		# Cleanup.
+		unlink $path if $scenario->{'is_archive'};
 	}
 }
 
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index b9e671fcda8..b0d73743cea 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -144,6 +144,8 @@ ArchiveOpts
 ArchiveShutdownCB
 ArchiveStartupCB
 ArchiveStreamState
+ArchivedWALEntry
+ArchivedWAL_hash
 ArchiverOutput
 ArchiverStage
 ArrayAnalyzeExtraData
@@ -3495,6 +3497,7 @@ astreamer_recovery_injector
 astreamer_tar_archiver
 astreamer_tar_parser
 astreamer_verify
+astreamer_waldump
 astreamer_zstd_frame
 auth_password_hook_typ
 autovac_table
-- 
2.47.1

From c2811b147d50a7e2e8f6566344e9f1f85614560d Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Thu, 6 Nov 2025 13:48:33 +0530
Subject: [PATCH v10 5/8] pg_waldump: Remove the restriction on the order of
 archived WAL files.

With previous patch, pg_waldump would stop decoding if WAL files were
not in the required sequence. With this patch, decoding will now
continue.  Any WAL file that is out of order will be written to a
temporary location, from which it will be read later. Once a temporary
file has been read, it will be removed.
---
 doc/src/sgml/ref/pg_waldump.sgml     |   8 +-
 src/bin/pg_waldump/archive_waldump.c | 230 ++++++++++++++++++++++++---
 src/bin/pg_waldump/pg_waldump.c      |  41 ++++-
 src/bin/pg_waldump/pg_waldump.h      |   4 +
 src/bin/pg_waldump/t/001_basic.pl    |   3 +-
 5 files changed, 264 insertions(+), 22 deletions(-)

diff --git a/doc/src/sgml/ref/pg_waldump.sgml b/doc/src/sgml/ref/pg_waldump.sgml
index d004bb0f67e..27adf77755c 100644
--- a/doc/src/sgml/ref/pg_waldump.sgml
+++ b/doc/src/sgml/ref/pg_waldump.sgml
@@ -149,8 +149,12 @@ PostgreSQL documentation
         of <envar>PGDATA</envar>.
        </para>
        <para>
-        If a tar archive is provided, its WAL segment files must be in
-        sequential order; otherwise, an error will be reported.
+        If a tar archive is provided and its WAL segment files are not in
+        sequential order, those files will be written to a temporary directory
+        named starting with <filename>waldump_tmp</filename>. This directory will be
+        created inside the directory specified by the <envar>TMPDIR</envar>
+        environment variable if it is set; otherwise, it will be created within
+        the same directory as the tar archive.
        </para>
       </listitem>
      </varlistentry>
diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
index 6ba067163d5..aa64da9a57d 100644
--- a/src/bin/pg_waldump/archive_waldump.c
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -17,6 +17,7 @@
 #include <unistd.h>
 
 #include "access/xlog_internal.h"
+#include "common/file_perm.h"
 #include "common/hashfn.h"
 #include "common/logging.h"
 #include "fe_utils/simple_list.h"
@@ -27,6 +28,9 @@
  */
 #define READ_CHUNK_SIZE				(128 * 1024)
 
+/* Temporary exported WAL file directory */
+static char *TmpWalSegDir = NULL;
+
 /* Hash entry structure for holding WAL segment data read from the archive */
 typedef struct ArchivedWALEntry
 {
@@ -64,6 +68,11 @@ typedef struct astreamer_waldump
 static int	read_archive_file(XLogDumpPrivate *privateInfo, Size count);
 static ArchivedWALEntry *get_archive_wal_entry(XLogSegNo segno,
 											   XLogDumpPrivate *privateInfo);
+static void setup_tmpseg_dir(const char *waldir);
+static void cleanup_tmpseg_dir_atexit(void);
+
+static FILE *prepare_tmp_write(XLogSegNo segno);
+static void perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file);
 
 static astreamer *astreamer_waldump_new(XLogDumpPrivate *privateInfo);
 static void astreamer_waldump_content(astreamer *streamer,
@@ -121,7 +130,9 @@ is_archive_file(const char *fname, pg_compress_algorithm *compression)
 /*
  * Initializes the tar archive reader, creates a hash table for WAL entries,
  * checks for existing valid WAL segments in the archive file and retrieves the
- * segment size, and sets up filters for relevant entries.
+ * segment size, and sets up filters for relevant entries. It also configures a
+ * temporary directory for out-of-order WAL data and registers an exit callback
+ * to clean up temporary files.
  */
 void
 init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
@@ -197,6 +208,13 @@ init_archive_reader(XLogDumpPrivate *privateInfo, const char *waldir,
 		privateInfo->endSegNo = UINT64_MAX;
 	else
 		XLByteToSeg(privateInfo->endptr, privateInfo->endSegNo, WalSegSz);
+
+	/*
+	 * Setup temporary directory to store WAL segments and set up an exit
+	 * callback to remove it upon completion.
+	 */
+	setup_tmpseg_dir(waldir);
+	atexit(cleanup_tmpseg_dir_atexit);
 }
 
 /*
@@ -370,15 +388,18 @@ read_archive_file(XLogDumpPrivate *privateInfo, Size count)
 }
 
 /*
- * Returns the archived WAL entry from the hash table if it exists. Otherwise,
+ * Returns the archived WAL entry from the hash table if it exists.  Otherwise,
  * it invokes the routine to read the archived file, which then populates the
- * entry in the hash table.
+ * entry in the hash table.  If the archive streamer happens to be reading a
+ * WAL from archive file that is not currently needed, that WAL data is written
+ * to a temporary file.
  */
 static ArchivedWALEntry *
 get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 {
 	ArchivedWALEntry *entry = NULL;
 	char		fname[MAXFNAMELEN];
+	FILE	   *write_fp = NULL;
 
 	/* Search hash table */
 	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
@@ -392,8 +413,11 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 		entry = privateInfo->cur_wal;
 
 		/* Fetch more data */
-		if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
-			break;			/* archive file ended */
+		if (entry == NULL || entry->buf.len == 0)
+		{
+			if (read_archive_file(privateInfo, READ_CHUNK_SIZE) == 0)
+				break;			/* archive file ended */
+		}
 
 		/*
 		 * Either, here for the first time, or the archived streamer is
@@ -419,20 +443,31 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 		}
 
 		/*
-		 * XXX: If the segment being read not the requested one, the data must
-		 * be buffered, as we currently lack the mechanism to write it to a
-		 * temporary file. This is a known limitation that will be fixed in the
-		 * next patch, as the buffer could grow up to the full WAL segment
-		 * size.
+		 * Archive streamer is currently reading a file that isn't the one
+		 * asked for, but it's required in the future. It should be written to
+		 * a temporary location for retrieval when needed.
 		 */
-		if (segno > entry->segno)
-			continue;
 
-		/* WAL segments must be archived in order */
-		pg_log_error("WAL files are not archived in sequential order");
-		pg_log_error_detail("Expecting segment number " UINT64_FORMAT " but found " UINT64_FORMAT ".",
-							segno, entry->segno);
-		exit(1);
+		/* Create a temporary file if one does not already exist */
+		if (!entry->tmpseg_exists)
+		{
+			write_fp = prepare_tmp_write(entry->segno);
+			entry->tmpseg_exists = true;
+		}
+
+		/* Flush data from the buffer to the file */
+		perform_tmp_write(entry->segno, &entry->buf, write_fp);
+		resetStringInfo(&entry->buf);
+
+		/*
+		 * The change in the current segment entry indicates that the reading
+		 * of this file has ended.
+		 */
+		if (entry != privateInfo->cur_wal && write_fp != NULL)
+		{
+			fclose(write_fp);
+			write_fp = NULL;
+		}
 	}
 
 	/* Requested WAL segment not found */
@@ -441,7 +476,166 @@ get_archive_wal_entry(XLogSegNo segno, XLogDumpPrivate *privateInfo)
 }
 
 /*
- * Create an astreamer that can read WAL from a tar file.
+ * Set up a temporary directory to temporarily store WAL segments.
+ */
+static void
+setup_tmpseg_dir(const char *waldir)
+{
+	char	   *template;
+
+	/*
+	 * Use the directory specified by the TMPDIR environment variable. If it's
+	 * not set, use the provided WAL directory to extract WAL file
+	 * temporarily.
+	 */
+	template = psprintf("%s/waldump_tmp-XXXXXX",
+						getenv("TMPDIR") ? getenv("TMPDIR") : waldir);
+	TmpWalSegDir = mkdtemp(template);
+
+	if (TmpWalSegDir == NULL)
+		pg_fatal("could not create directory \"%s\": %m", template);
+
+	canonicalize_path(TmpWalSegDir);
+
+	pg_log_debug("created directory \"%s\"", TmpWalSegDir);
+}
+
+/*
+ * Removes the temporarily store WAL segments, if any, at exiting.
+ */
+static void
+cleanup_tmpseg_dir_atexit(void)
+{
+	ArchivedWAL_iterator it;
+	ArchivedWALEntry *entry;
+
+	/* Remove temporary segments */
+	ArchivedWAL_start_iterate(ArchivedWAL_HTAB, &it);
+	while ((entry = ArchivedWAL_iterate(ArchivedWAL_HTAB, &it)) != NULL)
+	{
+		if (entry->tmpseg_exists)
+		{
+			remove_tmp_walseg(entry->segno, false);
+			entry->tmpseg_exists = false;
+		}
+	}
+
+	/* Remove temporary directory */
+	if (rmdir(TmpWalSegDir) == 0)
+		pg_log_debug("removed directory \"%s\"", TmpWalSegDir);
+}
+
+/*
+ * Generate the temporary WAL file path.
+ *
+ * Note that the caller is responsible to pfree it.
+ */
+char *
+get_tmp_walseg_path(XLogSegNo segno)
+{
+	char	   *fpath = (char *) palloc(MAXPGPATH);
+
+	Assert(TmpWalSegDir);
+
+	snprintf(fpath, MAXPGPATH, "%s/%08X%08X",
+			 TmpWalSegDir,
+			 (uint32) (segno / XLogSegmentsPerXLogId(WalSegSz)),
+			 (uint32) (segno % XLogSegmentsPerXLogId(WalSegSz)));
+
+	return fpath;
+}
+
+/*
+ * Routine to check whether a temporary file exists for the corresponding WAL
+ * segment number.
+ */
+bool
+tmp_walseg_exists(XLogSegNo segno)
+{
+	ArchivedWALEntry *entry;
+
+	entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+
+	if (entry == NULL)
+		return false;
+
+	return entry->tmpseg_exists;
+}
+
+/*
+ * Create an empty placeholder file and return its handle.
+ */
+static FILE *
+prepare_tmp_write(XLogSegNo segno)
+{
+	FILE	   *file;
+	char	   *fpath;
+
+	fpath = get_tmp_walseg_path(segno);
+
+	/* Create an empty placeholder */
+	file = fopen(fpath, PG_BINARY_W);
+	if (file == NULL)
+		pg_fatal("could not create file \"%s\": %m", fpath);
+
+#ifndef WIN32
+	if (chmod(fpath, pg_file_create_mode))
+		pg_fatal("could not set permissions on file \"%s\": %m",
+				 fpath);
+#endif
+
+	pg_log_debug("temporarily exporting file \"%s\"", fpath);
+	pfree(fpath);
+
+	return file;
+}
+
+/*
+ * Write buffer data to the given file handle.
+ */
+static void
+perform_tmp_write(XLogSegNo segno, StringInfo buf, FILE *file)
+{
+	Assert(file);
+
+	errno = 0;
+	if (buf->len > 0 && fwrite(buf->data, buf->len, 1, file) != 1)
+	{
+		/*
+		 * If write didn't set errno, assume problem is no disk space
+		 */
+		if (errno == 0)
+			errno = ENOSPC;
+		pg_fatal("could not write to file \"%s\": %m",
+				 get_tmp_walseg_path(segno));
+	}
+}
+
+/*
+ * Remove temporary file
+ */
+void
+remove_tmp_walseg(XLogSegNo segno, bool update_entry)
+{
+	char	   *fpath = get_tmp_walseg_path(segno);
+
+	if (unlink(fpath) == 0)
+		pg_log_debug("removed file \"%s\"", fpath);
+	pfree(fpath);
+
+	/* Update entry if requested */
+	if (update_entry)
+	{
+		ArchivedWALEntry *entry;
+
+		entry = ArchivedWAL_lookup(ArchivedWAL_HTAB, segno);
+		Assert(entry != NULL);
+		entry->tmpseg_exists = false;
+	}
+}
+
+/*
+ * Create an astreamer that can read WAL from tar file.
  */
 static astreamer *
 astreamer_waldump_new(XLogDumpPrivate *privateInfo)
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index e2c96c3f4ca..96d17e99690 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -474,12 +474,51 @@ TarWALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 {
 	XLogDumpPrivate *private = state->private_data;
 	int			count = required_read_len(private, targetPagePtr, reqLen);
+	XLogSegNo	nextSegNo;
 
 	/* Bail out if the count to be read is not valid */
 	if (count < 0)
 		return -1;
 
-	/* Read the WAL page from the archive streamer */
+	/*
+	 * If the target page is in a different segment, first check for the WAL
+	 * segment's physical existence in the temporary directory.
+	 */
+	nextSegNo = state->seg.ws_segno;
+	if (!XLByteInSeg(targetPagePtr, nextSegNo, WalSegSz))
+	{
+		if (state->seg.ws_file >= 0)
+		{
+			close(state->seg.ws_file);
+			state->seg.ws_file = -1;
+
+			/* Remove this file, as it is no longer needed. */
+			remove_tmp_walseg(nextSegNo, true);
+		}
+
+		XLByteToSeg(targetPagePtr, nextSegNo, WalSegSz);
+		state->seg.ws_tli = private->timeline;
+		state->seg.ws_segno = nextSegNo;
+
+		/*
+		 * If the next segment exists, open it and continue reading from there
+		 */
+		if (tmp_walseg_exists(nextSegNo))
+		{
+			char	   *fpath;
+
+			fpath = get_tmp_walseg_path(nextSegNo);
+			state->seg.ws_file = open(fpath, O_RDONLY | PG_BINARY, 0);
+			pfree(fpath);
+		}
+	}
+
+	/* Continue reading from the open WAL segment, if any */
+	if (state->seg.ws_file >= 0)
+		return WALDumpReadPage(state, targetPagePtr, count, targetPtr,
+							   readBuff);
+
+	/* Otherwise, read the WAL page from the archive streamer */
 	return read_archive_wal_page(private, targetPagePtr, count, readBuff);
 }
 
diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index ec7a33d40e0..03e02625ba1 100644
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -58,4 +58,8 @@ extern int	read_archive_wal_page(XLogDumpPrivate *privateInfo,
 								  XLogRecPtr targetPagePtr,
 								  Size count, char *readBuff);
 
+extern char *get_tmp_walseg_path(XLogSegNo segno);
+extern bool tmp_walseg_exists(XLogSegNo segno);
+extern void remove_tmp_walseg(XLogSegNo segno, bool update_entry);
+
 #endif							/* end of PG_WALDUMP_H */
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 13567fbdba1..68b0cdd29e5 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -7,6 +7,7 @@ use Cwd;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
 use Test::More;
+use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
 
@@ -272,7 +273,7 @@ sub generate_archive
 	}
 	closedir $dh;
 
-	@files = sort @files;
+	@files = shuffle @files;
 
 	# move into the WAL directory before archiving files
 	my $cwd = getcwd;
-- 
2.47.1

From 4f62c2263fb567811dd11b275d883ea1e0b7a4db Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Wed, 16 Jul 2025 14:47:43 +0530
Subject: [PATCH v10 6/8] pg_verifybackup: Delay default WAL directory
 preparation.

We are not sure whether to parse WAL from a directory or an archive
until the backup format is known. Therefore, we delay preparing the
default WAL directory until the point of parsing. This delay is
harmless, as the WAL directory is not used elsewhere.
---
 src/bin/pg_verifybackup/pg_verifybackup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 456e0375e13..c6be75eba74 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -285,10 +285,6 @@ main(int argc, char **argv)
 		manifest_path = psprintf("%s/backup_manifest",
 								 context.backup_directory);
 
-	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
-
 	/*
 	 * Try to read the manifest. We treat any errors encountered while parsing
 	 * the manifest as fatal; there doesn't seem to be much point in trying to
@@ -368,6 +364,10 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
+	/* By default, look for the WAL in the backup directory, too. */
+	if (wal_directory == NULL)
+		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
-- 
2.47.1

From d547aeb99303cc83cb1f8ad233804eb2e603d72e Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 25 Nov 2025 17:32:14 +0530
Subject: [PATCH v10 7/8] pg_verifybackup: Rename the wal-directory switch to
 wal-path

With previous patches to pg_waldump can now decode WAL directly from
tar files.  This means you'll be able to specify a tar archive path
instead of a traditional WAL directory.

To keep things consistent and more versatile, we should also
generalize the input switch for pg_verifybackup. It should accept
either a directory or a tar file path that contains WALs. This change
will also aligning it with the existing manifest-path switch naming.

== NOTE ==
  The corresponding PO files require updating due to this change.
---
 doc/src/sgml/ref/pg_verifybackup.sgml     |  2 +-
 src/bin/pg_verifybackup/pg_verifybackup.c | 22 +++++++++++-----------
 src/bin/pg_verifybackup/t/007_wal.pl      |  4 ++--
 3 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index 61c12975e4a..e9b8bfd51b1 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -261,7 +261,7 @@ PostgreSQL documentation
 
      <varlistentry>
       <term><option>-w <replaceable class="parameter">path</replaceable></option></term>
-      <term><option>--wal-directory=<replaceable class="parameter">path</replaceable></option></term>
+      <term><option>--wal-path=<replaceable class="parameter">path</replaceable></option></term>
       <listitem>
        <para>
         Try to parse WAL files stored in the specified directory, rather than
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index c6be75eba74..97178d585c3 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -93,7 +93,7 @@ static void verify_file_checksum(verifier_context *context,
 								 uint8 *buffer);
 static void parse_required_wal(verifier_context *context,
 							   char *pg_waldump_path,
-							   char *wal_directory);
+							   char *wal_path);
 static astreamer *create_archive_verifier(verifier_context *context,
 										  char *archive_name,
 										  Oid tblspc_oid,
@@ -126,7 +126,7 @@ main(int argc, char **argv)
 		{"progress", no_argument, NULL, 'P'},
 		{"quiet", no_argument, NULL, 'q'},
 		{"skip-checksums", no_argument, NULL, 's'},
-		{"wal-directory", required_argument, NULL, 'w'},
+		{"wal-path", required_argument, NULL, 'w'},
 		{NULL, 0, NULL, 0}
 	};
 
@@ -135,7 +135,7 @@ main(int argc, char **argv)
 	char	   *manifest_path = NULL;
 	bool		no_parse_wal = false;
 	bool		quiet = false;
-	char	   *wal_directory = NULL;
+	char	   *wal_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -221,8 +221,8 @@ main(int argc, char **argv)
 				context.skip_checksums = true;
 				break;
 			case 'w':
-				wal_directory = pstrdup(optarg);
-				canonicalize_path(wal_directory);
+				wal_path = pstrdup(optarg);
+				canonicalize_path(wal_path);
 				break;
 			default:
 				/* getopt_long already emitted a complaint */
@@ -365,15 +365,15 @@ main(int argc, char **argv)
 		verify_backup_checksums(&context);
 
 	/* By default, look for the WAL in the backup directory, too. */
-	if (wal_directory == NULL)
-		wal_directory = psprintf("%s/pg_wal", context.backup_directory);
+	if (wal_path == NULL)
+		wal_path = psprintf("%s/pg_wal", context.backup_directory);
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
 	 * not to do so.
 	 */
 	if (!no_parse_wal)
-		parse_required_wal(&context, pg_waldump_path, wal_directory);
+		parse_required_wal(&context, pg_waldump_path, wal_path);
 
 	/*
 	 * If everything looks OK, tell the user this, unless we were asked to
@@ -1198,7 +1198,7 @@ verify_file_checksum(verifier_context *context, manifest_file *m,
  */
 static void
 parse_required_wal(verifier_context *context, char *pg_waldump_path,
-				   char *wal_directory)
+				   char *wal_path)
 {
 	manifest_data *manifest = context->manifest;
 	manifest_wal_range *this_wal_range = manifest->first_wal_range;
@@ -1208,7 +1208,7 @@ parse_required_wal(verifier_context *context, char *pg_waldump_path,
 		char	   *pg_waldump_cmd;
 
 		pg_waldump_cmd = psprintf("\"%s\" --quiet --path=\"%s\" --timeline=%u --start=%X/%08X --end=%X/%08X\n",
-								  pg_waldump_path, wal_directory, this_wal_range->tli,
+								  pg_waldump_path, wal_path, this_wal_range->tli,
 								  LSN_FORMAT_ARGS(this_wal_range->start_lsn),
 								  LSN_FORMAT_ARGS(this_wal_range->end_lsn));
 		fflush(NULL);
@@ -1376,7 +1376,7 @@ usage(void)
 	printf(_("  -P, --progress              show progress information\n"));
 	printf(_("  -q, --quiet                 do not print any output, except for errors\n"));
 	printf(_("  -s, --skip-checksums        skip checksum verification\n"));
-	printf(_("  -w, --wal-directory=PATH    use specified path for WAL files\n"));
+	printf(_("  -w, --wal-path=PATH         use specified path for WAL files\n"));
 	printf(_("  -V, --version               output version information, then exit\n"));
 	printf(_("  -?, --help                  show this help, then exit\n"));
 	printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
diff --git a/src/bin/pg_verifybackup/t/007_wal.pl b/src/bin/pg_verifybackup/t/007_wal.pl
index 79087a1f6be..8ad2234453d 100644
--- a/src/bin/pg_verifybackup/t/007_wal.pl
+++ b/src/bin/pg_verifybackup/t/007_wal.pl
@@ -42,10 +42,10 @@ command_ok([ 'pg_verifybackup', '--no-parse-wal', $backup_path ],
 command_ok(
 	[
 		'pg_verifybackup',
-		'--wal-directory' => $relocated_pg_wal,
+		'--wal-path' => $relocated_pg_wal,
 		$backup_path
 	],
-	'--wal-directory can be used to specify WAL directory');
+	'--wal-path can be used to specify WAL directory');
 
 # Move directory back to original location.
 rename($relocated_pg_wal, $original_pg_wal) || die "rename pg_wal back: $!";
-- 
2.47.1

From 31791ed0320af216c80a8a72017670f0b0e06752 Mon Sep 17 00:00:00 2001
From: Amul Sul <sulamul@gmail.com>
Date: Tue, 25 Nov 2025 17:34:26 +0530
Subject: [PATCH v10 8/8] pg_verifybackup: enabled WAL parsing for tar-format
 backup

Now that pg_waldump supports decoding from tar archives, we should
leverage this functionality to remove the previous restriction on WAL
parsing for tar-backed formats.
---
 doc/src/sgml/ref/pg_verifybackup.sgml         |  5 +-
 src/bin/pg_verifybackup/pg_verifybackup.c     | 66 +++++++++++++------
 src/bin/pg_verifybackup/t/002_algorithm.pl    |  4 --
 src/bin/pg_verifybackup/t/003_corruption.pl   |  4 +-
 src/bin/pg_verifybackup/t/008_untar.pl        |  5 +-
 src/bin/pg_verifybackup/t/010_client_untar.pl |  5 +-
 6 files changed, 50 insertions(+), 39 deletions(-)

diff --git a/doc/src/sgml/ref/pg_verifybackup.sgml b/doc/src/sgml/ref/pg_verifybackup.sgml
index e9b8bfd51b1..16b50b5a4df 100644
--- a/doc/src/sgml/ref/pg_verifybackup.sgml
+++ b/doc/src/sgml/ref/pg_verifybackup.sgml
@@ -36,10 +36,7 @@ PostgreSQL documentation
    <literal>backup_manifest</literal> generated by the server at the time
    of the backup. The backup may be stored either in the "plain" or the "tar"
    format; this includes tar-format backups compressed with any algorithm
-   supported by <application>pg_basebackup</application>. However, at present,
-   <literal>WAL</literal> verification is supported only for plain-format
-   backups. Therefore, if the backup is stored in tar-format, the
-   <literal>-n, --no-parse-wal</literal> option should be used.
+   supported by <application>pg_basebackup</application>.
   </para>
 
   <para>
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
index 97178d585c3..baa5f9dfa5e 100644
--- a/src/bin/pg_verifybackup/pg_verifybackup.c
+++ b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -74,7 +74,9 @@ pg_noreturn static void report_manifest_error(JsonManifestParseContext *context,
 											  const char *fmt,...)
 			pg_attribute_printf(2, 3);
 
-static void verify_tar_backup(verifier_context *context, DIR *dir);
+static void verify_tar_backup(verifier_context *context, DIR *dir,
+							  char **base_archive_path,
+							  char **wal_archive_path);
 static void verify_plain_backup_directory(verifier_context *context,
 										  char *relpath, char *fullpath,
 										  DIR *dir);
@@ -83,7 +85,9 @@ static void verify_plain_backup_file(verifier_context *context, char *relpath,
 static void verify_control_file(const char *controlpath,
 								uint64 manifest_system_identifier);
 static void precheck_tar_backup_file(verifier_context *context, char *relpath,
-									 char *fullpath, SimplePtrList *tarfiles);
+									 char *fullpath, SimplePtrList *tarfiles,
+									 char **base_archive_path,
+									 char **wal_archive_path);
 static void verify_tar_file(verifier_context *context, char *relpath,
 							char *fullpath, astreamer *streamer);
 static void report_extra_backup_files(verifier_context *context);
@@ -136,6 +140,8 @@ main(int argc, char **argv)
 	bool		no_parse_wal = false;
 	bool		quiet = false;
 	char	   *wal_path = NULL;
+	char	   *base_archive_path = NULL;
+	char	   *wal_archive_path = NULL;
 	char	   *pg_waldump_path = NULL;
 	DIR		   *dir;
 
@@ -327,17 +333,6 @@ main(int argc, char **argv)
 		pfree(path);
 	}
 
-	/*
-	 * XXX: In the future, we should consider enhancing pg_waldump to read WAL
-	 * files from an archive.
-	 */
-	if (!no_parse_wal && context.format == 't')
-	{
-		pg_log_error("pg_waldump cannot read tar files");
-		pg_log_error_hint("You must use -n/--no-parse-wal when verifying a tar-format backup.");
-		exit(1);
-	}
-
 	/*
 	 * Perform the appropriate type of verification appropriate based on the
 	 * backup format. This will close 'dir'.
@@ -346,7 +341,7 @@ main(int argc, char **argv)
 		verify_plain_backup_directory(&context, NULL, context.backup_directory,
 									  dir);
 	else
-		verify_tar_backup(&context, dir);
+		verify_tar_backup(&context, dir, &base_archive_path, &wal_archive_path);
 
 	/*
 	 * The "matched" flag should now be set on every entry in the hash table.
@@ -364,9 +359,28 @@ main(int argc, char **argv)
 	if (context.format == 'p' && !context.skip_checksums)
 		verify_backup_checksums(&context);
 
-	/* By default, look for the WAL in the backup directory, too. */
+	/*
+	 * By default, WAL files are expected to be found in the backup directory
+	 * for plain-format backups. In the case of tar-format backups, if a
+	 * separate WAL archive is not found, the WAL files are most likely
+	 * included within the main data directory archive.
+	 */
 	if (wal_path == NULL)
-		wal_path = psprintf("%s/pg_wal", context.backup_directory);
+	{
+		if (context.format == 'p')
+			wal_path = psprintf("%s/pg_wal", context.backup_directory);
+		else if (wal_archive_path)
+			wal_path = wal_archive_path;
+		else if (base_archive_path)
+			wal_path = base_archive_path;
+		else
+		{
+			pg_log_error("WAL archive not found");
+			pg_log_error_hint("Specify the correct path using the option -w/--wal-path.  "
+							  "Or you must use -n/--no-parse-wal when verifying a tar-format backup.");
+			exit(1);
+		}
+	}
 
 	/*
 	 * Try to parse the required ranges of WAL records, unless we were told
@@ -787,7 +801,8 @@ verify_control_file(const char *controlpath, uint64 manifest_system_identifier)
  * close when we're done with it.
  */
 static void
-verify_tar_backup(verifier_context *context, DIR *dir)
+verify_tar_backup(verifier_context *context, DIR *dir, char **base_archive_path,
+				  char **wal_archive_path)
 {
 	struct dirent *dirent;
 	SimplePtrList tarfiles = {NULL, NULL};
@@ -816,7 +831,8 @@ verify_tar_backup(verifier_context *context, DIR *dir)
 			char	   *fullpath;
 
 			fullpath = psprintf("%s/%s", context->backup_directory, filename);
-			precheck_tar_backup_file(context, filename, fullpath, &tarfiles);
+			precheck_tar_backup_file(context, filename, fullpath, &tarfiles,
+									 base_archive_path, wal_archive_path);
 			pfree(fullpath);
 		}
 	}
@@ -875,11 +891,13 @@ verify_tar_backup(verifier_context *context, DIR *dir)
  *
  * The arguments to this function are mostly the same as the
  * verify_plain_backup_file. The additional argument outputs a list of valid
- * tar files.
+ * tar files, along with the full paths to the main archive and the WAL
+ * directory archive.
  */
 static void
 precheck_tar_backup_file(verifier_context *context, char *relpath,
-						 char *fullpath, SimplePtrList *tarfiles)
+						 char *fullpath, SimplePtrList *tarfiles,
+						 char **base_archive_path, char **wal_archive_path)
 {
 	struct stat sb;
 	Oid			tblspc_oid = InvalidOid;
@@ -918,9 +936,17 @@ precheck_tar_backup_file(verifier_context *context, char *relpath,
 	 * extension such as .gz, .lz4, or .zst.
 	 */
 	if (strncmp("base", relpath, 4) == 0)
+	{
 		suffix = relpath + 4;
+
+		*base_archive_path = pstrdup(fullpath);
+	}
 	else if (strncmp("pg_wal", relpath, 6) == 0)
+	{
 		suffix = relpath + 6;
+
+		*wal_archive_path = pstrdup(fullpath);
+	}
 	else
 	{
 		/* Expected a <tablespaceoid>.tar file here. */
diff --git a/src/bin/pg_verifybackup/t/002_algorithm.pl b/src/bin/pg_verifybackup/t/002_algorithm.pl
index 0556191ec9d..edc515d5904 100644
--- a/src/bin/pg_verifybackup/t/002_algorithm.pl
+++ b/src/bin/pg_verifybackup/t/002_algorithm.pl
@@ -30,10 +30,6 @@ sub test_checksums
 	{
 		# Add switch to get a tar-format backup
 		push @backup, ('--format' => 'tar');
-
-		# Add switch to skip WAL verification, which is not yet supported for
-		# tar-format backups
-		push @verify, ('--no-parse-wal');
 	}
 
 	# A backup with a bogus algorithm should fail.
diff --git a/src/bin/pg_verifybackup/t/003_corruption.pl b/src/bin/pg_verifybackup/t/003_corruption.pl
index b1d65b8aa0f..882d75d9dc2 100644
--- a/src/bin/pg_verifybackup/t/003_corruption.pl
+++ b/src/bin/pg_verifybackup/t/003_corruption.pl
@@ -193,10 +193,8 @@ for my $scenario (@scenario)
 			command_ok([ $tar, '-cf' => "$tar_backup_path/base.tar", '.' ]);
 			chdir($cwd) || die "chdir: $!";
 
-			# Now check that the backup no longer verifies. We must use -n
-			# here, because pg_waldump can't yet read WAL from a tarfile.
 			command_fails_like(
-				[ 'pg_verifybackup', '--no-parse-wal', $tar_backup_path ],
+				[ 'pg_verifybackup', $tar_backup_path ],
 				$scenario->{'fails_like'},
 				"corrupt backup fails verification: $name");
 
diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl
index ae67ae85a31..161c08c190d 100644
--- a/src/bin/pg_verifybackup/t/008_untar.pl
+++ b/src/bin/pg_verifybackup/t/008_untar.pl
@@ -47,7 +47,6 @@ my $tsoid = $primary->safe_psql(
 		SELECT oid FROM pg_tablespace WHERE spcname = 'regress_ts1'));
 
 my $backup_path = $primary->backup_dir . '/server-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -123,14 +122,12 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
 		rmtree($backup_path);
-		rmtree($extract_path);
 	}
 }
 
diff --git a/src/bin/pg_verifybackup/t/010_client_untar.pl b/src/bin/pg_verifybackup/t/010_client_untar.pl
index 1ac7b5db75a..9670fbe4fda 100644
--- a/src/bin/pg_verifybackup/t/010_client_untar.pl
+++ b/src/bin/pg_verifybackup/t/010_client_untar.pl
@@ -32,7 +32,6 @@ print $jf $junk_data;
 close $jf;
 
 my $backup_path = $primary->backup_dir . '/client-backup';
-my $extract_path = $primary->backup_dir . '/extracted-backup';
 
 my @test_configuration = (
 	{
@@ -137,13 +136,11 @@ for my $tc (@test_configuration)
 		# Verify tar backup.
 		$primary->command_ok(
 			[
-				'pg_verifybackup', '--no-parse-wal',
-				'--exit-on-error', $backup_path,
+				'pg_verifybackup', '--exit-on-error', $backup_path,
 			],
 			"verify backup, compression $method");
 
 		# Cleanup.
-		rmtree($extract_path);
 		rmtree($backup_path);
 	}
 }
-- 
2.47.1