Add contrib/pg_logicalsnapinspect

From 6c5a1ad66b203036739aae955932b8e3813c71e3 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Thu, 29 Aug 2024 20:51:31 +0000
Subject: [PATCH v2] Functions to get ondisk logical snapshots details

Provides SQL functions that allow to inspect the contents of serialized logical
snapshots of a running database cluster, which is useful for debugging or
educational purposes.
---
 contrib/test_decoding/Makefile                |   2 +-
 .../expected/get_ondisk_snapshot_info.out     |  57 +++++
 contrib/test_decoding/meson.build             |   1 +
 .../specs/get_ondisk_snapshot_info.spec       |  32 +++
 doc/src/sgml/func.sgml                        |  53 +++++
 src/backend/replication/logical/snapbuild.c   | 225 ++++++++++++++++++
 src/include/catalog/pg_proc.dat               |  16 ++
 7 files changed, 385 insertions(+), 1 deletion(-)
  17.3% contrib/test_decoding/expected/
  12.6% contrib/test_decoding/specs/
  17.3% doc/src/sgml/
  45.3% src/backend/replication/logical/
   6.6% src/include/catalog/

diff --git a/contrib/test_decoding/Makefile b/contrib/test_decoding/Makefile
index a4ba1a509a..b1b8ffa9e8 100644
--- a/contrib/test_decoding/Makefile
+++ b/contrib/test_decoding/Makefile
@@ -9,7 +9,7 @@ REGRESS = ddl xact rewrite toast permissions decoding_in_xact \
 ISOLATION = mxact delayed_startup ondisk_startup concurrent_ddl_dml \
 	oldest_xmin snapshot_transfer subxact_without_top concurrent_stream \
 	twophase_snapshot slot_creation_error catalog_change_snapshot \
-	skip_snapshot_restore
+	skip_snapshot_restore get_ondisk_snapshot_info
 
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/test_decoding/logical.conf
 ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/test_decoding/logical.conf
diff --git a/contrib/test_decoding/expected/get_ondisk_snapshot_info.out b/contrib/test_decoding/expected/get_ondisk_snapshot_info.out
new file mode 100644
index 0000000000..b676ccd528
--- /dev/null
+++ b/contrib/test_decoding/expected/get_ondisk_snapshot_info.out
@@ -0,0 +1,57 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2;
+state|catchange_count|array_length|committed_count|array_length
+-----+---------------+------------+---------------+------------
+    2|              0|            |              2|           2
+    2|              2|           2|              0|            
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f;
+count
+-----
+    2
+(1 row)
+
+?column?
+--------
+stop    
+(1 row)
+
diff --git a/contrib/test_decoding/meson.build b/contrib/test_decoding/meson.build
index f643dc81a2..d6e784cbdd 100644
--- a/contrib/test_decoding/meson.build
+++ b/contrib/test_decoding/meson.build
@@ -63,6 +63,7 @@ tests += {
       'twophase_snapshot',
       'slot_creation_error',
       'skip_snapshot_restore',
+      'get_ondisk_snapshot_info',
     ],
     'regress_args': [
       '--temp-config', files('logical.conf'),
diff --git a/contrib/test_decoding/specs/get_ondisk_snapshot_info.spec b/contrib/test_decoding/specs/get_ondisk_snapshot_info.spec
new file mode 100644
index 0000000000..39c2ee1430
--- /dev/null
+++ b/contrib/test_decoding/specs/get_ondisk_snapshot_info.spec
@@ -0,0 +1,32 @@
+# Test the functions that retrieve ondisk logical snapshots informations.
+# That needs some permutation to ensure that we are creating multiple logical
+# snapshots and that one of them contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f; }
+step "s1_get_logical_snapshot_info" { SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index 461fc3f437..8d233f092d 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -29682,6 +29682,59 @@ DETAIL:  Make sure pg_wal_replay_wait() isn't called within a transaction with a
       </entry>
       </row>
 
+      <row>
+       <entry id="pg-get-logical-snapshot-meta" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_get_logical_snapshot_meta</primary>
+        </indexterm>
+        <function>pg_get_logical_snapshot_meta</function> ( <parameter>in_lsn</parameter> <type>pg_lsn</type> )
+        <returnvalue>record</returnvalue>
+        ( <parameter>magic</parameter> <type>int</type>,
+        <parameter>checksum</parameter> <type>int</type>,
+        <parameter>version</parameter> <type>int</type> )
+       </para>
+       <para>
+        Gets logical snapshot metadata about a snapshot file that is located in
+        the <filename>pg_logical/snapshots</filename> directory.
+        The <replaceable>in_lsn</replaceable> argument can be extracted from the
+        snapshot file name. The aim of this function is mainly for debugging or
+        educational purposes.
+       </para>
+      </entry>
+      </row>
+
+      <row>
+       <entry id="pg-get-logical-snapshot-info" role="func_table_entry"><para role="func_signature">
+        <indexterm>
+         <primary>pg_get_logical_snapshot_info</primary>
+        </indexterm>
+        <function>pg_get_logical_snapshot_info</function> ( <parameter>in_lsn</parameter> <type>pg_lsn</type> )
+        <returnvalue>record</returnvalue>
+        ( <parameter>state</parameter> <type>smallint</type>,
+        <parameter>xmin</parameter> <type>xid</type>,
+        <parameter>xmax</parameter> <type>xid</type>,
+        <parameter>start_decoding_at</parameter> <type>pg_lsn</type>,
+        <parameter>two_phase_at</parameter> <type>pg_lsn</type>,
+        <parameter>initial_xmin_horizon</parameter> <type>xid</type>,
+        <parameter>building_full_snapshot</parameter> <type>boolean</type>,
+        <parameter>in_slot_creation</parameter> <type>boolean</type>,
+        <parameter>last_serialized_snapshot</parameter> <type>pg_lsn</type>,
+        <parameter>next_phase_at</parameter> <type>xid</type>,
+        <parameter>committed_count</parameter> <type>bigint</type>,
+        <parameter>committed_xip</parameter> <type>xid[]</type>,
+        <parameter>catchange_count</parameter> <type>bigint</type>,
+        <parameter>catchange_xip</parameter> <type>xid[]</type> )
+       </para>
+       <para>
+        Gets logical snapshot information about a snapshot file that is located
+        in the <filename>pg_logical/snapshots</filename> directory.
+        The <replaceable>in_lsn</replaceable> argument can be extracted from the
+        snapshot file name. The aim of this function is mainly for debugging or
+        educational purposes.
+       </para>
+      </entry>
+      </row>
+
      </tbody>
     </tgroup>
    </table>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..b4704dd5b4 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -129,6 +129,7 @@
 #include "access/transam.h"
 #include "access/xact.h"
 #include "common/file_utils.h"
+#include "funcapi.h"
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "replication/logical.h"
@@ -139,8 +140,10 @@
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "storage/standby.h"
+#include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/memutils.h"
+#include "utils/pg_lsn.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
 
@@ -1599,6 +1602,9 @@ typedef struct SnapBuildOnDisk
 #define SNAPBUILD_MAGIC 0x51A1E001
 #define SNAPBUILD_VERSION 6
 
+static void ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk,
+								 const char *path);
+
 /*
  * Store/Load a snapshot from disk, depending on the snapshot builder's state.
  *
@@ -2178,3 +2184,222 @@ SnapBuildSnapshotExists(XLogRecPtr lsn)
 
 	return ret == 0;
 }
+
+static void
+ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk, const char *path)
+{
+	int			fd;
+	Size		sz;
+	pg_crc32c	checksum;
+	MemoryContext context;
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"ondisk logical snapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		ereport(ERROR,
+				errmsg("file \"%s\" does not exist", path));
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	/* ----
+	 * Make sure the snapshot had been stored safely to disk, that's normally
+	 * cheap.
+	 * Note that we do not need PANIC here, nobody will be able to use the
+	 * slot without fsyncing, and saving it won't succeed without an fsync()
+	 * either...
+	 * ----
+	 */
+	fsync_fname(path, false);
+	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
+
+
+	/* read statically sized portion of snapshot */
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
+
+	if (ondisk->magic != SNAPBUILD_MAGIC)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
+
+	if (ondisk->version != SNAPBUILD_VERSION)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
+						path, ondisk->version, SNAPBUILD_VERSION)));
+
+	INIT_CRC32C(checksum);
+	COMP_CRC32C(checksum,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
+
+	/* read SnapBuild */
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
+
+	ondisk->builder.context = context;
+
+	/* restore committed xacts information */
+	if (ondisk->builder.committed.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
+	}
+
+	/* restore catalog modifying xacts information */
+	if (ondisk->builder.catchange.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
+	}
+
+	if (CloseTransientFile(fd) != 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not close file \"%s\": %m", path)));
+
+	FIN_CRC32C(checksum);
+
+	/* verify checksum of what we've read */
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[0] = Int32GetDatum(ondisk.magic);
+	values[1] = Int32GetDatum(ondisk.checksum);
+	values[2] = Int32GetDatum(ondisk.version);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+/*
+ * Retrieve the logical snapshot file data.
+ */
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[0] = Int16GetDatum(ondisk.builder.state);
+	values[1] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[2] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[3] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[4] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[5] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[6] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[7] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[8] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[9] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+	values[10] = Int64GetDatum(ondisk.builder.committed.xcnt);
+
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[11] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[11] = true;
+
+	values[12] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[13] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[13] = true;
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 85f42be1b3..76a8c00ba0 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11264,6 +11264,22 @@
   proargmodes => '{i,i,i,v,o,o,o}',
   proargnames => '{slot_name,upto_lsn,upto_nchanges,options,lsn,xid,data}',
   prosrc => 'pg_logical_slot_get_changes' },
+{ oid => '9080', descr => 'get logical snapshot file data',
+  proname => 'pg_get_logical_snapshot_info',
+  provolatile => 'i', proparallel => 's',
+  prorettype => 'record', proargtypes => 'pg_lsn',
+  proallargtypes => '{pg_lsn,int2,xid,xid,pg_lsn,pg_lsn,xid,bool,bool,pg_lsn,xid,int8,_int8,int8,_int8}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{in_lsn,state,xmin,xmax,start_decoding_at,two_phase_at,initial_xmin_horizon,building_full_snapshot,in_slot_creation,last_serialized_snapshot,next_phase_at,committed_count,committed_xip,catchange_count,catchange_xip}',
+  prosrc => 'pg_get_logical_snapshot_info' },
+{ oid => '9095', descr => 'get logical snapshot file metadata',
+  proname => 'pg_get_logical_snapshot_meta',
+  provolatile => 'i', proparallel => 's',
+  prorettype => 'record', proargtypes => 'pg_lsn',
+  proallargtypes => '{pg_lsn,int4,int4,int4}',
+  proargmodes => '{i,o,o,o}',
+  proargnames => '{in_lsn,magic,checksum,version}',
+  prosrc => 'pg_get_logical_snapshot_meta' },
 { oid => '3783', descr => 'get binary changes from replication slot',
   proname => 'pg_logical_slot_get_binary_changes', procost => '1000',
   prorows => '1000', provariadic => 'text', proisstrict => 'f',
-- 
2.34.1

From b51d403fa62af10f090c1e2339627e3ee29af524 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v3] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 +++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 249 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 145 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 190 +------------
 src/include/port/pg_crc32c.h                  |  16 +-
 src/include/replication/internal_snapbuild.h  | 204 ++++++++++++++
 src/include/replication/snapbuild.h           |   2 +-
 18 files changed, 826 insertions(+), 193 deletions(-)
   7.6% contrib/pg_logicalinspect/expected/
   5.7% contrib/pg_logicalinspect/specs/
  32.4% contrib/pg_logicalinspect/
  13.3% doc/src/sgml/
  17.4% src/backend/replication/logical/
   4.1% src/include/port/
  18.9% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..749cd4642d
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2;
+state|catchange_count|array_length|committed_count|array_length
+-----+---------------+------------+---------------+------------
+    2|              0|            |              2|           2
+    2|              2|           2|              0|            
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..b787dafc9b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect contents of logical snapshots',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..51713ed53e
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN in_lsn pg_lsn,
+    OUT magic int4,
+    OUT checksum int4,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN in_lsn pg_lsn,
+    OUT state int2,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..f3c1a0178e
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,249 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "port/pg_crc32c.h"
+#include "replication/internal_snapbuild.h"
+#include "utils/array.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+static void ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk,
+								 const char *path);
+
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in SnapBuildRestore() as well.
+ */
+
+/*
+ * Validate the logical snapshot file.
+ */
+static void
+ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk, const char *path)
+{
+	int			fd;
+	Size		sz;
+	pg_crc32c	checksum;
+	MemoryContext context;
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		ereport(ERROR,
+				errmsg("file \"%s\" does not exist", path));
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	/* ----
+	 * Make sure the snapshot had been stored safely to disk, that's normally
+	 * cheap.
+	 * Note that we do not need PANIC here, nobody will be able to use the
+	 * slot without fsyncing, and saving it won't succeed without an fsync()
+	 * either...
+	 * ----
+	 */
+	fsync_fname(path, false);
+	fsync_fname("pg_logical/snapshots", true);
+
+
+	/* read statically sized portion of snapshot */
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
+
+	if (ondisk->magic != SNAPBUILD_MAGIC)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
+
+	if (ondisk->version != SNAPBUILD_VERSION)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
+						path, ondisk->version, SNAPBUILD_VERSION)));
+
+	INIT_CRC32C(checksum);
+	COMP_CRC32C(checksum,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
+
+	/* read SnapBuild */
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
+
+	ondisk->builder.context = context;
+
+	/* restore committed xacts information */
+	if (ondisk->builder.committed.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
+	}
+
+	/* restore catalog modifying xacts information */
+	if (ondisk->builder.catchange.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
+	}
+
+	if (CloseTransientFile(fd) != 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not close file \"%s\": %m", path)));
+
+	FIN_CRC32C(checksum);
+
+	/* verify checksum of what we've read */
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "pg_logical/snapshots/%X-%X.snap",
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[0] = Int32GetDatum(ondisk.magic);
+	values[1] = Int32GetDatum(ondisk.checksum);
+	values[2] = Int32GetDatum(ondisk.version);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "pg_logical/snapshots/%X-%X.snap",
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[0] = Int16GetDatum(ondisk.builder.state);
+	values[1] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[2] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[3] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[4] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[5] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[6] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[7] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[8] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[9] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+	values[10] = Int64GetDatum(ondisk.builder.committed.xcnt);
+
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[11] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[11] = true;
+
+	values[12] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[13] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[13] = true;
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..e11eb63615
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+	CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+	DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f; }
+step "s1_get_logical_snapshot_info" { SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..7767de263f
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,145 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows to inspect serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <note>
+  <para>
+   The <filename>pg_logicalinspect</filename> functions are called
+   using an LSN argument that can be extracted from the output name of the
+   <function>pg_ls_logicalsnapdir</function>() function.
+  </para>
+ </note>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0/40796E18');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT (pg_get_logical_snapshot_meta(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0/40796E18');
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..a48c09c184 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -131,6 +131,7 @@
 #include "common/file_utils.h"
 #include "miscadmin.h"
 #include "pgstat.h"
+#include "replication/internal_snapbuild.h"
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -312,7 +173,6 @@ static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutof
 /* serialization functions */
 static void SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn);
 static bool SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn);
-static void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
 
 /*
  * Allocate a new snapshot builder.
@@ -1557,48 +1417,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
-#define SnapBuildOnDiskConstantSize \
-	offsetof(SnapBuildOnDisk, builder)
-#define SnapBuildOnDiskNotChecksummedSize \
-	offsetof(SnapBuildOnDisk, version)
-
-#define SNAPBUILD_MAGIC 0x51A1E001
-#define SNAPBUILD_VERSION 6
-
 /*
  * Store/Load a snapshot from disk, depending on the snapshot builder's state.
  *
@@ -1859,6 +1677,10 @@ out:
 /*
  * Restore a snapshot into 'builder' if previously one has been stored at the
  * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ *
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_logicalinspect contrib module
+ * as well.
  */
 static bool
 SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
@@ -2033,7 +1855,7 @@ snapshot_not_interesting:
 /*
  * Read the contents of the serialized snapshot to 'dest'.
  */
-static void
+void
 SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path)
 {
 	int			readBytes;
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 63c8e3a00b..cfc8c07944 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -47,7 +47,7 @@ typedef uint32 pg_crc32c;
 	((crc) = pg_comp_crc32c_sse42((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_ARMV8_CRC32C)
 /* Use ARMv8 CRC Extension instructions. */
@@ -56,7 +56,7 @@ extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_armv8((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_LOONGARCH_CRC32C)
 /* Use LoongArch CRCC instructions. */
@@ -65,7 +65,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_loongarch((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK) || defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
 
@@ -77,14 +77,14 @@ extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_
 	((crc) = pg_comp_crc32c((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
-extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
 
 #ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 #endif
 #ifdef USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 #endif
 
 #else
@@ -103,7 +103,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 #endif
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
 
 #endif
 
diff --git a/src/include/replication/internal_snapbuild.h b/src/include/replication/internal_snapbuild.h
new file mode 100644
index 0000000000..19a501c30f
--- /dev/null
+++ b/src/include/replication/internal_snapbuild.h
@@ -0,0 +1,204 @@
+/*-------------------------------------------------------------------------
+ *
+ * internal_snapbuild.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/internal_snapbuild.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef INTERNAL_SNAPBUILD_H
+#define INTERNAL_SNAPBUILD_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+#define SnapBuildOnDiskConstantSize \
+	offsetof(SnapBuildOnDisk, builder)
+#define SnapBuildOnDiskNotChecksummedSize \
+	offsetof(SnapBuildOnDisk, version)
+
+#define SNAPBUILD_MAGIC 0x51A1E001
+#define SNAPBUILD_VERSION 6
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+extern void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
+
+#endif							/* INTERNAL_SNAPBUILD_H */
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..fbe0798a41 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -46,7 +46,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include internal_snapbuild.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
-- 
2.34.1

From 7f824aae484f7275bb4119e1d5b060bce74c3058 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v4] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 +++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 248 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 145 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 190 +-------------
 src/include/port/pg_crc32c.h                  |  16 +-
 src/include/replication/snapbuild.h           |   2 +-
 src/include/replication/snapbuild_internal.h  | 204 ++++++++++++++
 18 files changed, 825 insertions(+), 193 deletions(-)
   7.6% contrib/pg_logicalinspect/expected/
   5.7% contrib/pg_logicalinspect/specs/
  32.3% contrib/pg_logicalinspect/
  13.3% doc/src/sgml/
  17.5% src/backend/replication/logical/
   4.1% src/include/port/
  19.0% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..749cd4642d
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2;
+state|catchange_count|array_length|committed_count|array_length
+-----+---------------+------------+---------------+------------
+    2|              0|            |              2|           2
+    2|              2|           2|              0|            
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..b787dafc9b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect contents of logical snapshots',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..51713ed53e
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN in_lsn pg_lsn,
+    OUT magic int4,
+    OUT checksum int4,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN in_lsn pg_lsn,
+    OUT state int2,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..74311b9d3b
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,248 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "port/pg_crc32c.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in SnapBuildRestore() as well.
+ */
+
+/*
+ * Validate the logical snapshot file.
+ */
+static void
+ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk, const char *path)
+{
+	int			fd;
+	Size		sz;
+	pg_crc32c	checksum;
+	MemoryContext context;
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		ereport(ERROR,
+				errmsg("file \"%s\" does not exist", path));
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	/* ----
+	 * Make sure the snapshot had been stored safely to disk, that's normally
+	 * cheap.
+	 * Note that we do not need PANIC here, nobody will be able to use the
+	 * slot without fsyncing, and saving it won't succeed without an fsync()
+	 * either...
+	 * ----
+	 */
+	fsync_fname(path, false);
+	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
+
+
+	/* read statically sized portion of snapshot */
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
+
+	if (ondisk->magic != SNAPBUILD_MAGIC)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
+
+	if (ondisk->version != SNAPBUILD_VERSION)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
+						path, ondisk->version, SNAPBUILD_VERSION)));
+
+	INIT_CRC32C(checksum);
+	COMP_CRC32C(checksum,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
+
+	/* read SnapBuild */
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
+
+	ondisk->builder.context = context;
+
+	/* restore committed xacts information */
+	if (ondisk->builder.committed.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
+	}
+
+	/* restore catalog modifying xacts information */
+	if (ondisk->builder.catchange.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
+	}
+
+	if (CloseTransientFile(fd) != 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not close file \"%s\": %m", path)));
+
+	FIN_CRC32C(checksum);
+
+	/* verify checksum of what we've read */
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[0] = Int32GetDatum(ondisk.magic);
+	values[1] = Int32GetDatum(ondisk.checksum);
+	values[2] = Int32GetDatum(ondisk.version);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[0] = Int16GetDatum(ondisk.builder.state);
+	values[1] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[2] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[3] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[4] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[5] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[6] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[7] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[8] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[9] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+	values[10] = Int64GetDatum(ondisk.builder.committed.xcnt);
+
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[11] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[11] = true;
+
+	values[12] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[13] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[13] = true;
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..e11eb63615
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+	CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+	DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f; }
+step "s1_get_logical_snapshot_info" { SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..7767de263f
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,145 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows to inspect serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <note>
+  <para>
+   The <filename>pg_logicalinspect</filename> functions are called
+   using an LSN argument that can be extracted from the output name of the
+   <function>pg_ls_logicalsnapdir</function>() function.
+  </para>
+ </note>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0/40796E18');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT (pg_get_logical_snapshot_meta(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0/40796E18');
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..bb7def9440 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -312,7 +173,6 @@ static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutof
 /* serialization functions */
 static void SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn);
 static bool SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn);
-static void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
 
 /*
  * Allocate a new snapshot builder.
@@ -1557,48 +1417,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
-#define SnapBuildOnDiskConstantSize \
-	offsetof(SnapBuildOnDisk, builder)
-#define SnapBuildOnDiskNotChecksummedSize \
-	offsetof(SnapBuildOnDisk, version)
-
-#define SNAPBUILD_MAGIC 0x51A1E001
-#define SNAPBUILD_VERSION 6
-
 /*
  * Store/Load a snapshot from disk, depending on the snapshot builder's state.
  *
@@ -1859,6 +1677,10 @@ out:
 /*
  * Restore a snapshot into 'builder' if previously one has been stored at the
  * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ *
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_logicalinspect contrib module
+ * as well.
  */
 static bool
 SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
@@ -2033,7 +1855,7 @@ snapshot_not_interesting:
 /*
  * Read the contents of the serialized snapshot to 'dest'.
  */
-static void
+void
 SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path)
 {
 	int			readBytes;
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 63c8e3a00b..cfc8c07944 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -47,7 +47,7 @@ typedef uint32 pg_crc32c;
 	((crc) = pg_comp_crc32c_sse42((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_ARMV8_CRC32C)
 /* Use ARMv8 CRC Extension instructions. */
@@ -56,7 +56,7 @@ extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_armv8((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_LOONGARCH_CRC32C)
 /* Use LoongArch CRCC instructions. */
@@ -65,7 +65,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_loongarch((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK) || defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
 
@@ -77,14 +77,14 @@ extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_
 	((crc) = pg_comp_crc32c((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
-extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
 
 #ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 #endif
 #ifdef USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 #endif
 
 #else
@@ -103,7 +103,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 #endif
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
 
 #endif
 
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..dbb4bc2f4b 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -46,7 +46,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..4d4d688470
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,204 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef INTERNAL_SNAPBUILD_H
+#define INTERNAL_SNAPBUILD_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+#define SnapBuildOnDiskConstantSize \
+	offsetof(SnapBuildOnDisk, builder)
+#define SnapBuildOnDiskNotChecksummedSize \
+	offsetof(SnapBuildOnDisk, version)
+
+#define SNAPBUILD_MAGIC 0x51A1E001
+#define SNAPBUILD_VERSION 6
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+extern void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
+
+#endif							/* INTERNAL_SNAPBUILD_H */
-- 
2.34.1

From ef6ce23b7145d3a1639dc776c56f0b94ae33bff0 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v5] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 +++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 253 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 145 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 190 +------------
 src/include/port/pg_crc32c.h                  |  16 +-
 src/include/replication/snapbuild.h           |   2 +-
 src/include/replication/snapbuild_internal.h  | 204 ++++++++++++++
 18 files changed, 830 insertions(+), 193 deletions(-)
   7.6% contrib/pg_logicalinspect/expected/
   5.7% contrib/pg_logicalinspect/specs/
  32.6% contrib/pg_logicalinspect/
  13.2% doc/src/sgml/
  17.4% src/backend/replication/logical/
   4.1% src/include/port/
  18.9% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..749cd4642d
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2;
+state|catchange_count|array_length|committed_count|array_length
+-----+---------------+------------+---------------+------------
+    2|              0|            |              2|           2
+    2|              2|           2|              0|            
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..b787dafc9b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect contents of logical snapshots',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..51713ed53e
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN in_lsn pg_lsn,
+    OUT magic int4,
+    OUT checksum int4,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN in_lsn pg_lsn,
+    OUT state int2,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..dc9041a619
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,253 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in SnapBuildRestore() as well.
+ */
+
+/*
+ * Validate the logical snapshot file.
+ */
+static void
+ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk, const char *path)
+{
+	int			fd;
+	Size		sz;
+	pg_crc32c	checksum;
+	MemoryContext context;
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		ereport(ERROR,
+				errmsg("file \"%s\" does not exist", path));
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	/* ----
+	 * Make sure the snapshot had been stored safely to disk, that's normally
+	 * cheap.
+	 * Note that we do not need PANIC here, nobody will be able to use the
+	 * slot without fsyncing, and saving it won't succeed without an fsync()
+	 * either...
+	 * ----
+	 */
+	fsync_fname(path, false);
+	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
+
+
+	/* read statically sized portion of snapshot */
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
+
+	if (ondisk->magic != SNAPBUILD_MAGIC)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
+
+	if (ondisk->version != SNAPBUILD_VERSION)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
+						path, ondisk->version, SNAPBUILD_VERSION)));
+
+	INIT_CRC32C(checksum);
+	COMP_CRC32C(checksum,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
+
+	/* read SnapBuild */
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
+
+	ondisk->builder.context = context;
+
+	/* restore committed xacts information */
+	if (ondisk->builder.committed.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
+	}
+
+	/* restore catalog modifying xacts information */
+	if (ondisk->builder.catchange.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
+	}
+
+	if (CloseTransientFile(fd) != 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not close file \"%s\": %m", path)));
+
+	FIN_CRC32C(checksum);
+
+	/* verify checksum of what we've read */
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = Int32GetDatum(ondisk.magic);
+	values[i++] = Int32GetDatum(ondisk.checksum);
+	values[i++] = Int32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = Int16GetDatum(ondisk.builder.state);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..e11eb63615
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+	CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+	DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f; }
+step "s1_get_logical_snapshot_info" { SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..7767de263f
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,145 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows to inspect serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <note>
+  <para>
+   The <filename>pg_logicalinspect</filename> functions are called
+   using an LSN argument that can be extracted from the output name of the
+   <function>pg_ls_logicalsnapdir</function>() function.
+  </para>
+ </note>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0/40796E18');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT (pg_get_logical_snapshot_meta(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0/40796E18');
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..bb7def9440 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -312,7 +173,6 @@ static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutof
 /* serialization functions */
 static void SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn);
 static bool SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn);
-static void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
 
 /*
  * Allocate a new snapshot builder.
@@ -1557,48 +1417,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
-#define SnapBuildOnDiskConstantSize \
-	offsetof(SnapBuildOnDisk, builder)
-#define SnapBuildOnDiskNotChecksummedSize \
-	offsetof(SnapBuildOnDisk, version)
-
-#define SNAPBUILD_MAGIC 0x51A1E001
-#define SNAPBUILD_VERSION 6
-
 /*
  * Store/Load a snapshot from disk, depending on the snapshot builder's state.
  *
@@ -1859,6 +1677,10 @@ out:
 /*
  * Restore a snapshot into 'builder' if previously one has been stored at the
  * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ *
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_logicalinspect contrib module
+ * as well.
  */
 static bool
 SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
@@ -2033,7 +1855,7 @@ snapshot_not_interesting:
 /*
  * Read the contents of the serialized snapshot to 'dest'.
  */
-static void
+void
 SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path)
 {
 	int			readBytes;
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 63c8e3a00b..cfc8c07944 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -47,7 +47,7 @@ typedef uint32 pg_crc32c;
 	((crc) = pg_comp_crc32c_sse42((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_ARMV8_CRC32C)
 /* Use ARMv8 CRC Extension instructions. */
@@ -56,7 +56,7 @@ extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_armv8((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_LOONGARCH_CRC32C)
 /* Use LoongArch CRCC instructions. */
@@ -65,7 +65,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_loongarch((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK) || defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
 
@@ -77,14 +77,14 @@ extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_
 	((crc) = pg_comp_crc32c((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
-extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
 
 #ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 #endif
 #ifdef USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 #endif
 
 #else
@@ -103,7 +103,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 #endif
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
 
 #endif
 
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..dbb4bc2f4b 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -46,7 +46,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..4d4d688470
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,204 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef INTERNAL_SNAPBUILD_H
+#define INTERNAL_SNAPBUILD_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+#define SnapBuildOnDiskConstantSize \
+	offsetof(SnapBuildOnDisk, builder)
+#define SnapBuildOnDiskNotChecksummedSize \
+	offsetof(SnapBuildOnDisk, version)
+
+#define SNAPBUILD_MAGIC 0x51A1E001
+#define SNAPBUILD_VERSION 6
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+extern void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
+
+#endif							/* INTERNAL_SNAPBUILD_H */
-- 
2.34.1

From a4e1432f9ccd02b999fb62619dcde3b0d9ad164f Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v6] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 +++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 254 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 145 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 190 +------------
 src/include/port/pg_crc32c.h                  |  16 +-
 src/include/replication/snapbuild.h           |   2 +-
 src/include/replication/snapbuild_internal.h  | 204 ++++++++++++++
 18 files changed, 831 insertions(+), 193 deletions(-)
   7.6% contrib/pg_logicalinspect/expected/
   5.7% contrib/pg_logicalinspect/specs/
  32.6% contrib/pg_logicalinspect/
  13.2% doc/src/sgml/
  17.4% src/backend/replication/logical/
   4.1% src/include/port/
  18.9% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..749cd4642d
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2;
+state|catchange_count|array_length|committed_count|array_length
+-----+---------------+------------+---------------+------------
+    2|              0|            |              2|           2
+    2|              2|           2|              0|            
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..b787dafc9b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect contents of logical snapshots',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..51713ed53e
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN in_lsn pg_lsn,
+    OUT magic int4,
+    OUT checksum int4,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN in_lsn pg_lsn,
+    OUT state int2,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..8fba5cbda6
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,254 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in SnapBuildRestore() as well.
+ */
+
+/*
+ * Validate the logical snapshot file.
+ */
+static void
+ValidateAndRestoreSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk,
+							   const char *path)
+{
+	int			fd;
+	Size		sz;
+	pg_crc32c	checksum;
+	MemoryContext context;
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		ereport(ERROR,
+				errmsg("file \"%s\" does not exist", path));
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	/* ----
+	 * Make sure the snapshot had been stored safely to disk, that's normally
+	 * cheap.
+	 * Note that we do not need PANIC here, nobody will be able to use the
+	 * slot without fsyncing, and saving it won't succeed without an fsync()
+	 * either...
+	 * ----
+	 */
+	fsync_fname(path, false);
+	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
+
+
+	/* read statically sized portion of snapshot */
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
+
+	if (ondisk->magic != SNAPBUILD_MAGIC)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
+
+	if (ondisk->version != SNAPBUILD_VERSION)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
+						path, ondisk->version, SNAPBUILD_VERSION)));
+
+	INIT_CRC32C(checksum);
+	COMP_CRC32C(checksum,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
+
+	/* read SnapBuild */
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
+
+	ondisk->builder.context = context;
+
+	/* restore committed xacts information */
+	if (ondisk->builder.committed.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
+	}
+
+	/* restore catalog modifying xacts information */
+	if (ondisk->builder.catchange.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
+	}
+
+	if (CloseTransientFile(fd) != 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not close file \"%s\": %m", path)));
+
+	FIN_CRC32C(checksum);
+
+	/* verify checksum of what we've read */
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = Int32GetDatum(ondisk.magic);
+	values[i++] = Int32GetDatum(ondisk.checksum);
+	values[i++] = Int32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = Int16GetDatum(ondisk.builder.state);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+		narrayelems = 0;
+
+		for (narrayelems = 0; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..e11eb63615
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+	CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+	DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f; }
+step "s1_get_logical_snapshot_info" { SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..ce3c688b4f
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,145 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows to inspect serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <note>
+  <para>
+   The <filename>pg_logicalinspect</filename> functions are called
+   using an LSN argument that can be extracted from the output name of the
+   <function>pg_ls_logicalsnapdir</function>() function.
+  </para>
+ </note>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0/40796E18');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT (pg_get_logical_snapshot_meta(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0/40796E18');
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..bb7def9440 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -312,7 +173,6 @@ static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutof
 /* serialization functions */
 static void SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn);
 static bool SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn);
-static void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
 
 /*
  * Allocate a new snapshot builder.
@@ -1557,48 +1417,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
-#define SnapBuildOnDiskConstantSize \
-	offsetof(SnapBuildOnDisk, builder)
-#define SnapBuildOnDiskNotChecksummedSize \
-	offsetof(SnapBuildOnDisk, version)
-
-#define SNAPBUILD_MAGIC 0x51A1E001
-#define SNAPBUILD_VERSION 6
-
 /*
  * Store/Load a snapshot from disk, depending on the snapshot builder's state.
  *
@@ -1859,6 +1677,10 @@ out:
 /*
  * Restore a snapshot into 'builder' if previously one has been stored at the
  * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ *
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_logicalinspect contrib module
+ * as well.
  */
 static bool
 SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
@@ -2033,7 +1855,7 @@ snapshot_not_interesting:
 /*
  * Read the contents of the serialized snapshot to 'dest'.
  */
-static void
+void
 SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path)
 {
 	int			readBytes;
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 63c8e3a00b..cfc8c07944 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -47,7 +47,7 @@ typedef uint32 pg_crc32c;
 	((crc) = pg_comp_crc32c_sse42((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_ARMV8_CRC32C)
 /* Use ARMv8 CRC Extension instructions. */
@@ -56,7 +56,7 @@ extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_armv8((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_LOONGARCH_CRC32C)
 /* Use LoongArch CRCC instructions. */
@@ -65,7 +65,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_loongarch((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK) || defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
 
@@ -77,14 +77,14 @@ extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_
 	((crc) = pg_comp_crc32c((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
-extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
 
 #ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 #endif
 #ifdef USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 #endif
 
 #else
@@ -103,7 +103,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 #endif
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
 
 #endif
 
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..dbb4bc2f4b 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -46,7 +46,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..2b332303c2
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,204 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+#define SnapBuildOnDiskConstantSize \
+	offsetof(SnapBuildOnDisk, builder)
+#define SnapBuildOnDiskNotChecksummedSize \
+	offsetof(SnapBuildOnDisk, version)
+
+#define SNAPBUILD_MAGIC 0x51A1E001
+#define SNAPBUILD_VERSION 6
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+extern void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
index dc9041a..2111202 100644
--- a/contrib/pg_logicalinspect/pg_logicalinspect.c
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -1,13 +1,17 @@
 /*-------------------------------------------------------------------------
  *
  * pg_logicalinspect.c
- *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *		Functions to inspect contents of PostgreSQL logical snapshots
  *
  * Copyright (c) 2024, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
- *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *		contrib/pg_logicalinspect/pg_logicalinspect.c
  *
+ *
+ * NOTES
+ * 		For any code change or issue fix here, it is highly recommended to
+ * 		give a thought about doing the same in SnapBuildRestore() as well.
  *-------------------------------------------------------------------------
  */
 #include "postgres.h"
@@ -23,18 +27,12 @@ PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
 PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
 
 /*
- * NOTE: For any code change or issue fix here, it is highly recommended to
- * give a thought about doing the same in SnapBuildRestore() as well.
- */
-
-/*
  * Validate the logical snapshot file.
  */
 static void
 ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk, const char *path)
 {
 	int			fd;
-	Size		sz;
 	pg_crc32c	checksum;
 	MemoryContext context;
 
@@ -63,7 +61,6 @@ ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk, const char *path)
 	fsync_fname(path, false);
 	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
 
-
 	/* read statically sized portion of snapshot */
 	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
 
@@ -93,7 +90,7 @@ ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk, const char *path)
 	/* restore committed xacts information */
 	if (ondisk->builder.committed.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		Size sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
 		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
 		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
 		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
@@ -102,7 +99,7 @@ ValidateSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk, const char *path)
 	/* restore catalog modifying xacts information */
 	if (ondisk->builder.catchange.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		Size sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
 		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
 		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
 		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
@@ -210,12 +207,11 @@ pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
 	if (ondisk.builder.committed.xcnt > 0)
 	{
 		Datum	   *arrayelems;
-		int			narrayelems;
+		int			narrayelems = 0;
 
 		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
-		narrayelems = 0;
 
-		for (narrayelems = 0; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+		for (; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
 			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
 
 		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
@@ -228,12 +224,11 @@ pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
 	if (ondisk.builder.catchange.xcnt > 0)
 	{
 		Datum	   *arrayelems;
-		int			narrayelems;
+		int			narrayelems = 0;
 
 		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
-		narrayelems = 0;
 
-		for (narrayelems = 0; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+		for (; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
 			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
 
 		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
index 7767de2..3cc7742 100644
--- a/doc/src/sgml/pglogicalinspect.sgml
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -10,7 +10,7 @@
  <para>
   The <filename>pg_logicalinspect</filename> module provides SQL functions
   that allow you to inspect the contents of logical decoding components. It
-  allows to inspect serialized logical snapshots of a running
+  allows the inspection of serialized logical snapshots of a running
   <productname>PostgreSQL</productname> database cluster, which is useful
   for debugging or educational purposes.
  </para>
@@ -38,7 +38,7 @@
       the <filename>pg_logical/snapshots</filename> directory.
       The <replaceable>in_lsn</replaceable> argument can be extracted from the
       snapshot file name.
-      example:
+      For example:
 <screen>
 postgres=# SELECT * FROM pg_ls_logicalsnapdir();
 -[ RECORD 1 ]+-----------------------
@@ -79,7 +79,7 @@ version  | 6
       the <filename>pg_logical/snapshots</filename> directory.
       The <replaceable>in_lsn</replaceable> argument can be extracted from the
       snapshot file name.
-      example:
+      For example:
 <screen>
 postgres=# SELECT * FROM pg_ls_logicalsnapdir();
 -[ RECORD 1 ]+-----------------------

From dc62ef7632874a60ff388e68d5c0cb67675c87a5 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v7] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 +++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 251 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 145 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 190 +------------
 src/include/port/pg_crc32c.h                  |  16 +-
 src/include/replication/snapbuild.h           |   2 +-
 src/include/replication/snapbuild_internal.h  | 204 ++++++++++++++
 18 files changed, 828 insertions(+), 193 deletions(-)
   7.6% contrib/pg_logicalinspect/expected/
   5.7% contrib/pg_logicalinspect/specs/
  32.5% contrib/pg_logicalinspect/
  13.3% doc/src/sgml/
  17.4% src/backend/replication/logical/
   4.1% src/include/port/
  18.9% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..749cd4642d
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2;
+state|catchange_count|array_length|committed_count|array_length
+-----+---------------+------------+---------------+------------
+    2|              0|            |              2|           2
+    2|              2|           2|              0|            
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..b787dafc9b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect contents of logical snapshots',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..51713ed53e
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN in_lsn pg_lsn,
+    OUT magic int4,
+    OUT checksum int4,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN in_lsn pg_lsn,
+    OUT state int2,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..185f36a72c
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,251 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in SnapBuildRestore() as well.
+ */
+
+/*
+ * Validate the logical snapshot file.
+ */
+static void
+ValidateAndRestoreSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk,
+							   const char *path)
+{
+	int			fd;
+	Size		sz;
+	pg_crc32c	checksum;
+	MemoryContext context;
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		ereport(ERROR,
+				errmsg("file \"%s\" does not exist", path));
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	/* ----
+	 * Make sure the snapshot had been stored safely to disk, that's normally
+	 * cheap.
+	 * Note that we do not need PANIC here, nobody will be able to use the
+	 * slot without fsyncing, and saving it won't succeed without an fsync()
+	 * either...
+	 * ----
+	 */
+	fsync_fname(path, false);
+	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
+
+	/* read statically sized portion of snapshot */
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
+
+	if (ondisk->magic != SNAPBUILD_MAGIC)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
+
+	if (ondisk->version != SNAPBUILD_VERSION)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
+						path, ondisk->version, SNAPBUILD_VERSION)));
+
+	INIT_CRC32C(checksum);
+	COMP_CRC32C(checksum,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
+
+	/* read SnapBuild */
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
+
+	ondisk->builder.context = context;
+
+	/* restore committed xacts information */
+	if (ondisk->builder.committed.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
+	}
+
+	/* restore catalog modifying xacts information */
+	if (ondisk->builder.catchange.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
+	}
+
+	if (CloseTransientFile(fd) != 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not close file \"%s\": %m", path)));
+
+	FIN_CRC32C(checksum);
+
+	/* verify checksum of what we've read */
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = Int32GetDatum(ondisk.magic);
+	values[i++] = Int32GetDatum(ondisk.checksum);
+	values[i++] = Int32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = Int16GetDatum(ondisk.builder.state);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..e11eb63615
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+	CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+	DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f; }
+step "s1_get_logical_snapshot_info" { SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1),(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..06c627df52
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,145 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <note>
+  <para>
+   The <filename>pg_logicalinspect</filename> functions are called
+   using an LSN argument that can be extracted from the output name of the
+   <function>pg_ls_logicalsnapdir</function>() function.
+  </para>
+ </note>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0/40796E18');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT (pg_get_logical_snapshot_meta(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0/40796E18');
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]------------+-----------
+state                    | 2
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..bb7def9440 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -312,7 +173,6 @@ static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutof
 /* serialization functions */
 static void SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn);
 static bool SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn);
-static void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
 
 /*
  * Allocate a new snapshot builder.
@@ -1557,48 +1417,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
-#define SnapBuildOnDiskConstantSize \
-	offsetof(SnapBuildOnDisk, builder)
-#define SnapBuildOnDiskNotChecksummedSize \
-	offsetof(SnapBuildOnDisk, version)
-
-#define SNAPBUILD_MAGIC 0x51A1E001
-#define SNAPBUILD_VERSION 6
-
 /*
  * Store/Load a snapshot from disk, depending on the snapshot builder's state.
  *
@@ -1859,6 +1677,10 @@ out:
 /*
  * Restore a snapshot into 'builder' if previously one has been stored at the
  * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ *
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_logicalinspect contrib module
+ * as well.
  */
 static bool
 SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
@@ -2033,7 +1855,7 @@ snapshot_not_interesting:
 /*
  * Read the contents of the serialized snapshot to 'dest'.
  */
-static void
+void
 SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path)
 {
 	int			readBytes;
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 63c8e3a00b..cfc8c07944 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -47,7 +47,7 @@ typedef uint32 pg_crc32c;
 	((crc) = pg_comp_crc32c_sse42((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_ARMV8_CRC32C)
 /* Use ARMv8 CRC Extension instructions. */
@@ -56,7 +56,7 @@ extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_armv8((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_LOONGARCH_CRC32C)
 /* Use LoongArch CRCC instructions. */
@@ -65,7 +65,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_loongarch((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK) || defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
 
@@ -77,14 +77,14 @@ extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_
 	((crc) = pg_comp_crc32c((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
-extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
 
 #ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 #endif
 #ifdef USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 #endif
 
 #else
@@ -103,7 +103,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 #endif
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
 
 #endif
 
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..dbb4bc2f4b 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -46,7 +46,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..0e47ddfcb4
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,204 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+#define SnapBuildOnDiskConstantSize \
+	offsetof(SnapBuildOnDisk, builder)
+#define SnapBuildOnDiskNotChecksummedSize \
+	offsetof(SnapBuildOnDisk, version)
+
+#define SNAPBUILD_MAGIC 0x51A1E001
+#define SNAPBUILD_VERSION 6
+
+extern void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
index 185f36a..308c653 100644
--- a/contrib/pg_logicalinspect/pg_logicalinspect.c
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -205,8 +205,8 @@ pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
 	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
 	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
 	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
-	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
 
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
 	if (ondisk.builder.committed.xcnt > 0)
 	{
 		Datum	   *arrayelems;
@@ -223,7 +223,6 @@ pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
 		nulls[i++] = true;
 
 	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
-
 	if (ondisk.builder.catchange.xcnt > 0)
 	{
 		Datum	   *arrayelems;

From 42204dbf1b073e2ef0f7476979d5ebadb5201a5e Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v8] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 ++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 265 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 151 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 190 +------------
 src/include/port/pg_crc32c.h                  |  16 +-
 src/include/replication/snapbuild.h           |   6 +-
 src/include/replication/snapbuild_internal.h  | 204 ++++++++++++++
 18 files changed, 852 insertions(+), 193 deletions(-)
   7.8% contrib/pg_logicalinspect/expected/
   5.7% contrib/pg_logicalinspect/specs/
  32.9% contrib/pg_logicalinspect/
  13.6% doc/src/sgml/
  16.9% src/backend/replication/logical/
   4.0% src/include/port/
  18.7% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..08de273197
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1) AS catchange_array_length,(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) AS committed_array_length FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2;
+state     |catchange_count|catchange_array_length|committed_count|committed_array_length
+----------+---------------+----------------------+---------------+----------------------
+consistent|              0|                      |              2|                     2
+consistent|              2|                     2|              0|                      
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..3ec635509b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect logical decoding components',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..760b0d53f4
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN in_lsn pg_lsn,
+    OUT magic int4,
+    OUT checksum int4,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN in_lsn pg_lsn,
+    OUT state text,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..100b82fd46
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,265 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/*
+ * Lookup table for SnapBuildState.
+ */
+
+#define SNAPBUILD_STATE_INCR 1
+
+static const char *const SnapBuildStateDesc[] = {
+	[SNAPBUILD_START + SNAPBUILD_STATE_INCR] = "start",
+	[SNAPBUILD_BUILDING_SNAPSHOT + SNAPBUILD_STATE_INCR] = "building",
+	[SNAPBUILD_FULL_SNAPSHOT + SNAPBUILD_STATE_INCR] = "full",
+	[SNAPBUILD_CONSISTENT + SNAPBUILD_STATE_INCR] = "consistent",
+};
+
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in SnapBuildRestore() as well.
+ */
+
+/*
+ * Validate the logical snapshot file and read its contents to 'ondisk'.
+ */
+static void
+ValidateAndRestoreSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk,
+							   const char *path)
+{
+	int			fd;
+	Size		sz;
+	pg_crc32c	checksum;
+	MemoryContext context;
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		ereport(ERROR,
+				errmsg("file \"%s\" does not exist", path));
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	/* ----
+	 * Make sure the snapshot had been stored safely to disk, that's normally
+	 * cheap.
+	 * Note that we do not need PANIC here, nobody will be able to use the
+	 * slot without fsyncing, and saving it won't succeed without an fsync()
+	 * either...
+	 * ----
+	 */
+	fsync_fname(path, false);
+	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
+
+	/* read statically sized portion of snapshot */
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
+
+	if (ondisk->magic != SNAPBUILD_MAGIC)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
+
+	if (ondisk->version != SNAPBUILD_VERSION)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
+						path, ondisk->version, SNAPBUILD_VERSION)));
+
+	INIT_CRC32C(checksum);
+	COMP_CRC32C(checksum,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
+
+	/* read SnapBuild */
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
+
+	ondisk->builder.context = context;
+
+	/* restore committed xacts information */
+	if (ondisk->builder.committed.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
+	}
+
+	/* restore catalog modifying xacts information */
+	if (ondisk->builder.catchange.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
+	}
+
+	if (CloseTransientFile(fd) != 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not close file \"%s\": %m", path)));
+
+	FIN_CRC32C(checksum);
+
+	/* verify checksum of what we've read */
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = Int32GetDatum(ondisk.magic);
+	values[i++] = Int32GetDatum(ondisk.checksum);
+	values[i++] = Int32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = CStringGetTextDatum(SnapBuildStateDesc[ondisk.builder.state +
+														 SNAPBUILD_STATE_INCR]);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..47641163fe
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+    CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+    DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f; }
+step "s1_get_logical_snapshot_info" { SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1) AS catchange_array_length,(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) AS committed_array_length FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..f0b26637d0
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,151 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <note>
+  <para>
+   The <filename>pg_logicalinspect</filename> functions are called
+   using an LSN argument that can be extracted from the output name of the
+   <function>pg_ls_logicalsnapdir</function>() function.
+  </para>
+ </note>
+
+ <para>
+  By default, use of these functions is restricted to superusers and members of
+  the <literal>pg_read_server_files</literal> role. Access may be granted by
+  superusers to others using <command>GRANT</command>.
+ </para>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0/40796E18');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT (pg_get_logical_snapshot_meta(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0/40796E18');
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..bb7def9440 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -312,7 +173,6 @@ static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutof
 /* serialization functions */
 static void SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn);
 static bool SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn);
-static void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
 
 /*
  * Allocate a new snapshot builder.
@@ -1557,48 +1417,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
-#define SnapBuildOnDiskConstantSize \
-	offsetof(SnapBuildOnDisk, builder)
-#define SnapBuildOnDiskNotChecksummedSize \
-	offsetof(SnapBuildOnDisk, version)
-
-#define SNAPBUILD_MAGIC 0x51A1E001
-#define SNAPBUILD_VERSION 6
-
 /*
  * Store/Load a snapshot from disk, depending on the snapshot builder's state.
  *
@@ -1859,6 +1677,10 @@ out:
 /*
  * Restore a snapshot into 'builder' if previously one has been stored at the
  * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ *
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_logicalinspect contrib module
+ * as well.
  */
 static bool
 SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
@@ -2033,7 +1855,7 @@ snapshot_not_interesting:
 /*
  * Read the contents of the serialized snapshot to 'dest'.
  */
-static void
+void
 SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path)
 {
 	int			readBytes;
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 63c8e3a00b..cfc8c07944 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -47,7 +47,7 @@ typedef uint32 pg_crc32c;
 	((crc) = pg_comp_crc32c_sse42((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_ARMV8_CRC32C)
 /* Use ARMv8 CRC Extension instructions. */
@@ -56,7 +56,7 @@ extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_armv8((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_LOONGARCH_CRC32C)
 /* Use LoongArch CRCC instructions. */
@@ -65,7 +65,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_loongarch((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK) || defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
 
@@ -77,14 +77,14 @@ extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_
 	((crc) = pg_comp_crc32c((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
-extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
 
 #ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 #endif
 #ifdef USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 #endif
 
 #else
@@ -103,7 +103,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 #endif
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
 
 #endif
 
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..78df2d1079 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -15,6 +15,10 @@
 #include "access/xlogdefs.h"
 #include "utils/snapmgr.h"
 
+/*
+ * Please keep SnapBuildStateDesc[] (located in the pg_logicalinspect module)
+ * updated should a change needs to be done in SnapBuildState.
+ */
 typedef enum
 {
 	/*
@@ -46,7 +50,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..0e47ddfcb4
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,204 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+#define SnapBuildOnDiskConstantSize \
+	offsetof(SnapBuildOnDisk, builder)
+#define SnapBuildOnDiskNotChecksummedSize \
+	offsetof(SnapBuildOnDisk, version)
+
+#define SNAPBUILD_MAGIC 0x51A1E001
+#define SNAPBUILD_VERSION 6
+
+extern void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
index 100b82f..2419df1 100644
--- a/contrib/pg_logicalinspect/pg_logicalinspect.c
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -24,19 +24,6 @@ PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
 PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
 
 /*
- * Lookup table for SnapBuildState.
- */
-
-#define SNAPBUILD_STATE_INCR 1
-
-static const char *const SnapBuildStateDesc[] = {
-	[SNAPBUILD_START + SNAPBUILD_STATE_INCR] = "start",
-	[SNAPBUILD_BUILDING_SNAPSHOT + SNAPBUILD_STATE_INCR] = "building",
-	[SNAPBUILD_FULL_SNAPSHOT + SNAPBUILD_STATE_INCR] = "full",
-	[SNAPBUILD_CONSISTENT + SNAPBUILD_STATE_INCR] = "consistent",
-};
-
-/*
  * NOTE: For any code change or issue fix here, it is highly recommended to
  * give a thought about doing the same in SnapBuildRestore() as well.
  */
@@ -186,6 +173,16 @@ Datum
 pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
 {
 #define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	/*
+	 * Lookup table for SnapBuildState. The lookup index is offset by 1
+	 * because the consecutive SnapBuildState enum values start at -1.
+	 */
+	static const char *const SnapBuildStateDesc[] = {
+		[1 + SNAPBUILD_START] = "start",
+		[1 + SNAPBUILD_BUILDING_SNAPSHOT] = "building",
+		[1 + SNAPBUILD_FULL_SNAPSHOT] = "full",
+		[1 + SNAPBUILD_CONSISTENT] = "consistent",
+	};
 	SnapBuildOnDisk ondisk;
 	XLogRecPtr	lsn;
 	HeapTuple	tuple;
@@ -209,8 +206,7 @@ pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
 
 	memset(nulls, 0, sizeof(nulls));
 
-	values[i++] = CStringGetTextDatum(SnapBuildStateDesc[ondisk.builder.state +
-														 SNAPBUILD_STATE_INCR]);
+	values[i++] = CStringGetTextDatum(SnapBuildStateDesc[ondisk.builder.state + 1]);
 	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
 	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
 	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index 78df2d1..e844a89 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -17,7 +17,7 @@
 
 /*
  * Please keep SnapBuildStateDesc[] (located in the pg_logicalinspect module)
- * updated should a change needs to be done in SnapBuildState.
+ * updated if a change needs to be made to SnapBuildState.
  */
 typedef enum
 {

From ae831c9042244f7da6a78d5e350d9c30672f1cd5 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v9] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 ++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 265 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 151 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 190 +------------
 src/include/port/pg_crc32c.h                  |  16 +-
 src/include/replication/snapbuild.h           |   6 +-
 src/include/replication/snapbuild_internal.h  | 204 ++++++++++++++
 18 files changed, 852 insertions(+), 193 deletions(-)
   7.8% contrib/pg_logicalinspect/expected/
   5.7% contrib/pg_logicalinspect/specs/
  33.1% contrib/pg_logicalinspect/
  13.6% doc/src/sgml/
  16.8% src/backend/replication/logical/
   4.0% src/include/port/
  18.6% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..08de273197
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1) AS catchange_array_length,(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) AS committed_array_length FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2;
+state     |catchange_count|catchange_array_length|committed_count|committed_array_length
+----------+---------------+----------------------+---------------+----------------------
+consistent|              0|                      |              2|                     2
+consistent|              2|                     2|              0|                      
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..3ec635509b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect logical decoding components',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..fc06e428ce
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN in_lsn pg_lsn,
+    OUT magic int4,
+    OUT checksum int8,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN in_lsn pg_lsn,
+    OUT state text,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..770249425e
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,265 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/*
+ * Lookup table for SnapBuildState. The lookup index is offset by 1
+ * because the consecutive SnapBuildState enum values start at -1.
+ */
+#define SNAPBUILD_STATE_INCR 1
+
+static const char *const SnapBuildStateDesc[] = {
+	[SNAPBUILD_START + SNAPBUILD_STATE_INCR] = "start",
+	[SNAPBUILD_BUILDING_SNAPSHOT + SNAPBUILD_STATE_INCR] = "building",
+	[SNAPBUILD_FULL_SNAPSHOT + SNAPBUILD_STATE_INCR] = "full",
+	[SNAPBUILD_CONSISTENT + SNAPBUILD_STATE_INCR] = "consistent",
+};
+
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in SnapBuildRestore() as well.
+ */
+
+/*
+ * Validate the logical snapshot file and read its contents to 'ondisk'.
+ */
+static void
+ValidateAndRestoreSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk,
+							   const char *path)
+{
+	int			fd;
+	Size		sz;
+	pg_crc32c	checksum;
+	MemoryContext context;
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		ereport(ERROR,
+				errmsg("file \"%s\" does not exist", path));
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	/* ----
+	 * Make sure the snapshot had been stored safely to disk, that's normally
+	 * cheap.
+	 * Note that we do not need PANIC here, nobody will be able to use the
+	 * slot without fsyncing, and saving it won't succeed without an fsync()
+	 * either...
+	 * ----
+	 */
+	fsync_fname(path, false);
+	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
+
+	/* read statically sized portion of snapshot */
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
+
+	if (ondisk->magic != SNAPBUILD_MAGIC)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
+
+	if (ondisk->version != SNAPBUILD_VERSION)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
+						path, ondisk->version, SNAPBUILD_VERSION)));
+
+	INIT_CRC32C(checksum);
+	COMP_CRC32C(checksum,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
+
+	/* read SnapBuild */
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
+
+	ondisk->builder.context = context;
+
+	/* restore committed xacts information */
+	if (ondisk->builder.committed.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
+	}
+
+	/* restore catalog modifying xacts information */
+	if (ondisk->builder.catchange.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
+	}
+
+	if (CloseTransientFile(fd) != 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not close file \"%s\": %m", path)));
+
+	FIN_CRC32C(checksum);
+
+	/* verify checksum of what we've read */
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = UInt32GetDatum(ondisk.magic);
+	values[i++] = Int64GetDatum((int64) ondisk.checksum);
+	values[i++] = UInt32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = CStringGetTextDatum(SnapBuildStateDesc[ondisk.builder.state +
+														 SNAPBUILD_STATE_INCR]);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..47641163fe
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+    CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+    DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f; }
+step "s1_get_logical_snapshot_info" { SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1) AS catchange_array_length,(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) AS committed_array_length FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..f0b26637d0
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,151 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <note>
+  <para>
+   The <filename>pg_logicalinspect</filename> functions are called
+   using an LSN argument that can be extracted from the output name of the
+   <function>pg_ls_logicalsnapdir</function>() function.
+  </para>
+ </note>
+
+ <para>
+  By default, use of these functions is restricted to superusers and members of
+  the <literal>pg_read_server_files</literal> role. Access may be granted by
+  superusers to others using <command>GRANT</command>.
+ </para>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0/40796E18');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT (pg_get_logical_snapshot_meta(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0/40796E18');
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..bb7def9440 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -312,7 +173,6 @@ static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutof
 /* serialization functions */
 static void SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn);
 static bool SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn);
-static void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
 
 /*
  * Allocate a new snapshot builder.
@@ -1557,48 +1417,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
-#define SnapBuildOnDiskConstantSize \
-	offsetof(SnapBuildOnDisk, builder)
-#define SnapBuildOnDiskNotChecksummedSize \
-	offsetof(SnapBuildOnDisk, version)
-
-#define SNAPBUILD_MAGIC 0x51A1E001
-#define SNAPBUILD_VERSION 6
-
 /*
  * Store/Load a snapshot from disk, depending on the snapshot builder's state.
  *
@@ -1859,6 +1677,10 @@ out:
 /*
  * Restore a snapshot into 'builder' if previously one has been stored at the
  * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ *
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_logicalinspect contrib module
+ * as well.
  */
 static bool
 SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
@@ -2033,7 +1855,7 @@ snapshot_not_interesting:
 /*
  * Read the contents of the serialized snapshot to 'dest'.
  */
-static void
+void
 SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path)
 {
 	int			readBytes;
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 63c8e3a00b..cfc8c07944 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -47,7 +47,7 @@ typedef uint32 pg_crc32c;
 	((crc) = pg_comp_crc32c_sse42((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_ARMV8_CRC32C)
 /* Use ARMv8 CRC Extension instructions. */
@@ -56,7 +56,7 @@ extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_armv8((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_LOONGARCH_CRC32C)
 /* Use LoongArch CRCC instructions. */
@@ -65,7 +65,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_loongarch((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK) || defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
 
@@ -77,14 +77,14 @@ extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_
 	((crc) = pg_comp_crc32c((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
-extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
 
 #ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 #endif
 #ifdef USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 #endif
 
 #else
@@ -103,7 +103,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 #endif
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
 
 #endif
 
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..e844a89882 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -15,6 +15,10 @@
 #include "access/xlogdefs.h"
 #include "utils/snapmgr.h"
 
+/*
+ * Please keep SnapBuildStateDesc[] (located in the pg_logicalinspect module)
+ * updated if a change needs to be made to SnapBuildState.
+ */
 typedef enum
 {
 	/*
@@ -46,7 +50,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..0e47ddfcb4
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,204 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+#define SnapBuildOnDiskConstantSize \
+	offsetof(SnapBuildOnDisk, builder)
+#define SnapBuildOnDiskNotChecksummedSize \
+	offsetof(SnapBuildOnDisk, version)
+
+#define SNAPBUILD_MAGIC 0x51A1E001
+#define SNAPBUILD_VERSION 6
+
+extern void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

From a093c768f1b3a70c80046742d7a264bee5d4d205 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v10] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 +++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 262 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 151 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 190 +------------
 src/include/port/pg_crc32c.h                  |  16 +-
 src/include/replication/snapbuild.h           |   6 +-
 src/include/replication/snapbuild_internal.h  | 204 ++++++++++++++
 18 files changed, 849 insertions(+), 193 deletions(-)
   7.8% contrib/pg_logicalinspect/expected/
   5.7% contrib/pg_logicalinspect/specs/
  32.9% contrib/pg_logicalinspect/
  13.6% doc/src/sgml/
  16.9% src/backend/replication/logical/
   4.0% src/include/port/
  18.7% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..08de273197
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1) AS catchange_array_length,(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) AS committed_array_length FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2;
+state     |catchange_count|catchange_array_length|committed_count|committed_array_length
+----------+---------------+----------------------+---------------+----------------------
+consistent|              0|                      |              2|                     2
+consistent|              2|                     2|              0|                      
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..3ec635509b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect logical decoding components',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..fc06e428ce
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN in_lsn pg_lsn,
+    OUT magic int4,
+    OUT checksum int8,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(pg_lsn) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN in_lsn pg_lsn,
+    OUT state text,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(pg_lsn) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..4460f07a36
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,262 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/*
+ * Lookup table for SnapBuildState. The lookup index is offset by 1
+ * because the consecutive SnapBuildState enum values start at -1.
+ */
+#define SNAPBUILD_STATE_INCR 1
+
+static const char *const SnapBuildStateDesc[] = {
+	[SNAPBUILD_START + SNAPBUILD_STATE_INCR] = "start",
+	[SNAPBUILD_BUILDING_SNAPSHOT + SNAPBUILD_STATE_INCR] = "building",
+	[SNAPBUILD_FULL_SNAPSHOT + SNAPBUILD_STATE_INCR] = "full",
+	[SNAPBUILD_CONSISTENT + SNAPBUILD_STATE_INCR] = "consistent",
+};
+
+/*
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in SnapBuildRestore() as well.
+ */
+
+/*
+ * Validate the logical snapshot file and read its contents to 'ondisk'.
+ */
+static void
+ValidateAndRestoreSnapshotFile(XLogRecPtr lsn, SnapBuildOnDisk *ondisk,
+							   const char *path)
+{
+	int			fd;
+	Size		sz;
+	pg_crc32c	checksum;
+	MemoryContext context;
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	/* ----
+	 * Make sure the snapshot had been stored safely to disk, that's normally
+	 * cheap.
+	 * Note that we do not need PANIC here, nobody will be able to use the
+	 * slot without fsyncing, and saving it won't succeed without an fsync()
+	 * either...
+	 * ----
+	 */
+	fsync_fname(path, false);
+	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
+
+	/* read statically sized portion of snapshot */
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
+
+	if (ondisk->magic != SNAPBUILD_MAGIC)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
+
+	if (ondisk->version != SNAPBUILD_VERSION)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
+						path, ondisk->version, SNAPBUILD_VERSION)));
+
+	INIT_CRC32C(checksum);
+	COMP_CRC32C(checksum,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
+
+	/* read SnapBuild */
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
+
+	ondisk->builder.context = context;
+
+	/* restore committed xacts information */
+	if (ondisk->builder.committed.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
+	}
+
+	/* restore catalog modifying xacts information */
+	if (ondisk->builder.catchange.xcnt > 0)
+	{
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(ondisk->builder.context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
+	}
+
+	if (CloseTransientFile(fd) != 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not close file \"%s\": %m", path)));
+
+	FIN_CRC32C(checksum);
+
+	/* verify checksum of what we've read */
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = UInt32GetDatum(ondisk.magic);
+	values[i++] = Int64GetDatum((int64) ondisk.checksum);
+	values[i++] = UInt32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	XLogRecPtr	lsn;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+
+	lsn = PG_GETARG_LSN(0);
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	ValidateAndRestoreSnapshotFile(lsn, &ondisk, path);
+
+	/* Build a tuple descriptor for our result type. */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = CStringGetTextDatum(SnapBuildStateDesc[ondisk.builder.state +
+														 SNAPBUILD_STATE_INCR]);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(ondisk.builder.context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..47641163fe
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+    CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+    DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT((pg_get_logical_snapshot_meta(f.name::pg_lsn))) FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f; }
+step "s1_get_logical_snapshot_info" { SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).state,(pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).catchange_xip,1) AS catchange_array_length,(pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_count,array_length((pg_get_logical_snapshot_info(f.name::pg_lsn)).committed_xip,1) AS committed_array_length FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name FROM pg_ls_logicalsnapdir()) AS f ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..f0b26637d0
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,151 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <note>
+  <para>
+   The <filename>pg_logicalinspect</filename> functions are called
+   using an LSN argument that can be extracted from the output name of the
+   <function>pg_ls_logicalsnapdir</function>() function.
+  </para>
+ </note>
+
+ <para>
+  By default, use of these functions is restricted to superusers and members of
+  the <literal>pg_read_server_files</literal> role. Access may be granted by
+  superusers to others using <command>GRANT</command>.
+ </para>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0/40796E18');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT (pg_get_logical_snapshot_meta(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(in_lsn pg_lsn) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>in_lsn</replaceable> argument can be extracted from the
+      snapshot file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0/40796E18');
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT (pg_get_logical_snapshot_info(f.name::pg_lsn)).*
+           FROM (SELECT replace(replace(name,'.snap',''),'-','/') AS name
+                 FROM pg_ls_logicalsnapdir()) AS f;
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>in_lsn</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..bb7def9440 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -312,7 +173,6 @@ static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutof
 /* serialization functions */
 static void SnapBuildSerialize(SnapBuild *builder, XLogRecPtr lsn);
 static bool SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn);
-static void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
 
 /*
  * Allocate a new snapshot builder.
@@ -1557,48 +1417,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
-#define SnapBuildOnDiskConstantSize \
-	offsetof(SnapBuildOnDisk, builder)
-#define SnapBuildOnDiskNotChecksummedSize \
-	offsetof(SnapBuildOnDisk, version)
-
-#define SNAPBUILD_MAGIC 0x51A1E001
-#define SNAPBUILD_VERSION 6
-
 /*
  * Store/Load a snapshot from disk, depending on the snapshot builder's state.
  *
@@ -1859,6 +1677,10 @@ out:
 /*
  * Restore a snapshot into 'builder' if previously one has been stored at the
  * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ *
+ * NOTE: For any code change or issue fix here, it is highly recommended to
+ * give a thought about doing the same in pg_logicalinspect contrib module
+ * as well.
  */
 static bool
 SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
@@ -2033,7 +1855,7 @@ snapshot_not_interesting:
 /*
  * Read the contents of the serialized snapshot to 'dest'.
  */
-static void
+void
 SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path)
 {
 	int			readBytes;
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 63c8e3a00b..cfc8c07944 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -47,7 +47,7 @@ typedef uint32 pg_crc32c;
 	((crc) = pg_comp_crc32c_sse42((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_ARMV8_CRC32C)
 /* Use ARMv8 CRC Extension instructions. */
@@ -56,7 +56,7 @@ extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_armv8((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_LOONGARCH_CRC32C)
 /* Use LoongArch CRCC instructions. */
@@ -65,7 +65,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 	((crc) = pg_comp_crc32c_loongarch((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_t len);
 
 #elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK) || defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
 
@@ -77,14 +77,14 @@ extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_
 	((crc) = pg_comp_crc32c((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
-extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
 
 #ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
 #endif
 #ifdef USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK
-extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len);
 #endif
 
 #else
@@ -103,7 +103,7 @@ extern pg_crc32c pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t le
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 #endif
 
-extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
+extern PGDLLIMPORT pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len);
 
 #endif
 
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..e844a89882 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -15,6 +15,10 @@
 #include "access/xlogdefs.h"
 #include "utils/snapmgr.h"
 
+/*
+ * Please keep SnapBuildStateDesc[] (located in the pg_logicalinspect module)
+ * updated if a change needs to be made to SnapBuildState.
+ */
 typedef enum
 {
 	/*
@@ -46,7 +50,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..0e47ddfcb4
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,204 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+#define SnapBuildOnDiskConstantSize \
+	offsetof(SnapBuildOnDisk, builder)
+#define SnapBuildOnDiskNotChecksummedSize \
+	offsetof(SnapBuildOnDisk, version)
+
+#define SNAPBUILD_MAGIC 0x51A1E001
+#define SNAPBUILD_VERSION 6
+
+extern void SnapBuildRestoreContents(int fd, char *dest, Size size, const char *path);
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

From 52fbead00e079132881ec51a3f913cd784ccd356 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v11] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 ++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 199 +++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 150 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 279 ++++--------------
 src/include/replication/snapbuild.h           |   6 +-
 src/include/replication/snapbuild_internal.h  | 197 +++++++++++++
 17 files changed, 823 insertions(+), 221 deletions(-)
   7.5% contrib/pg_logicalinspect/expected/
   5.2% contrib/pg_logicalinspect/specs/
  27.9% contrib/pg_logicalinspect/
  14.2% doc/src/sgml/
  25.0% src/backend/replication/logical/
  19.7% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..219afd6a16
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT info.state,info.catchange_count,array_length(info.catchange_xip,1) AS catchange_array_length,info.committed_count,array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
+state     |catchange_count|catchange_array_length|committed_count|committed_array_length
+----------+---------------+----------------------+---------------+----------------------
+consistent|              0|                      |              2|                     2
+consistent|              2|                     2|              0|                      
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..3ec635509b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect logical decoding components',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..c773f6e458
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN filename text,
+    OUT magic int4,
+    OUT checksum int8,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN filename text,
+    OUT state text,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..0e3e1f50fc
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,199 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/* Return the description of SnapBuildState */
+static const char *
+get_snapbuild_state_desc(SnapBuildState state)
+{
+	const char *stateDesc = "unknown state";
+
+	switch (state)
+	{
+		case SNAPBUILD_START:
+			stateDesc = "start";
+			break;
+		case SNAPBUILD_BUILDING_SNAPSHOT:
+			stateDesc = "building";
+			break;
+		case SNAPBUILD_FULL_SNAPSHOT:
+			stateDesc = "full";
+			break;
+		case SNAPBUILD_CONSISTENT:
+			stateDesc = "consistent";
+			break;
+	}
+
+	return stateDesc;
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	MemoryContext context;
+	int			fd;
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	ValidateAndRestoreSnapshotFile(&ondisk, path, fd, context);
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = UInt32GetDatum(ondisk.magic);
+	values[i++] = Int64GetDatum((int64) ondisk.checksum);
+	values[i++] = UInt32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	MemoryContext context;
+	int			fd;
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	ValidateAndRestoreSnapshotFile(&ondisk, path, fd, context);
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = CStringGetTextDatum(get_snapbuild_state_desc(ondisk.builder.state));
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..7dc3cd7504
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+    CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+    DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
+step "s1_get_logical_snapshot_info" { SELECT info.state,info.catchange_count,array_length(info.catchange_xip,1) AS catchange_array_length,info.committed_count,array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..bb2cb0485a
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,150 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <note>
+  <para>
+   The <filename>pg_logicalinspect</filename> functions are called
+   using a text argument that can be extracted from the output name of the
+   <function>pg_ls_logicalsnapdir</function>() function.
+  </para>
+ </note>
+
+ <para>
+  By default, use of these functions is restricted to superusers and members of
+  the <literal>pg_read_server_files</literal> role. Access may be granted by
+  superusers to others using <command>GRANT</command>.
+ </para>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0-40796E18.snap');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT meta.* FROM pg_ls_logicalsnapdir(),
+pg_get_logical_snapshot_meta(name) AS meta;
+
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0-40796E18.snap');
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT info.* FROM pg_ls_logicalsnapdir(),
+pg_get_logical_snapshot_info(name) AS info;
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..7a3b963a2f 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -1557,40 +1418,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
 #define SnapBuildOnDiskConstantSize \
 	offsetof(SnapBuildOnDisk, builder)
 #define SnapBuildOnDiskNotChecksummedSize \
@@ -1857,34 +1684,14 @@ out:
 }
 
 /*
- * Restore a snapshot into 'builder' if previously one has been stored at the
- * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ * Validate the logical snapshot file and read its contents to 'ondisk'.
  */
-static bool
-SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+void
+ValidateAndRestoreSnapshotFile(SnapBuildOnDisk *ondisk, const char *path, int fd,
+							   MemoryContext context)
 {
-	SnapBuildOnDisk ondisk;
-	int			fd;
-	char		path[MAXPGPATH];
-	Size		sz;
 	pg_crc32c	checksum;
-
-	/* no point in loading a snapshot if we're already there */
-	if (builder->state == SNAPBUILD_CONSISTENT)
-		return false;
-
-	sprintf(path, "%s/%X-%X.snap",
-			PG_LOGICAL_SNAPSHOTS_DIR,
-			LSN_FORMAT_ARGS(lsn));
-
-	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
-
-	if (fd < 0 && errno == ENOENT)
-		return false;
-	else if (fd < 0)
-		ereport(ERROR,
-				(errcode_for_file_access(),
-				 errmsg("could not open file \"%s\": %m", path)));
+	Size		sz;
 
 	/* ----
 	 * Make sure the snapshot had been stored safely to disk, that's normally
@@ -1897,47 +1704,46 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	fsync_fname(path, false);
 	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
 
-
 	/* read statically sized portion of snapshot */
-	SnapBuildRestoreContents(fd, (char *) &ondisk, SnapBuildOnDiskConstantSize, path);
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
 
-	if (ondisk.magic != SNAPBUILD_MAGIC)
+	if (ondisk->magic != SNAPBUILD_MAGIC)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
-						path, ondisk.magic, SNAPBUILD_MAGIC)));
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
 
-	if (ondisk.version != SNAPBUILD_VERSION)
+	if (ondisk->version != SNAPBUILD_VERSION)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
-						path, ondisk.version, SNAPBUILD_VERSION)));
+						path, ondisk->version, SNAPBUILD_VERSION)));
 
 	INIT_CRC32C(checksum);
 	COMP_CRC32C(checksum,
-				((char *) &ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
 				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
 
 	/* read SnapBuild */
-	SnapBuildRestoreContents(fd, (char *) &ondisk.builder, sizeof(SnapBuild), path);
-	COMP_CRC32C(checksum, &ondisk.builder, sizeof(SnapBuild));
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
 
 	/* restore committed xacts information */
-	if (ondisk.builder.committed.xcnt > 0)
+	if (ondisk->builder.committed.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.committed.xcnt;
-		ondisk.builder.committed.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.committed.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.committed.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
 	}
 
 	/* restore catalog modifying xacts information */
-	if (ondisk.builder.catchange.xcnt > 0)
+	if (ondisk->builder.catchange.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.catchange.xcnt;
-		ondisk.builder.catchange.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.catchange.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.catchange.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
 	}
 
 	if (CloseTransientFile(fd) != 0)
@@ -1948,11 +1754,44 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	FIN_CRC32C(checksum);
 
 	/* verify checksum of what we've read */
-	if (!EQ_CRC32C(checksum, ondisk.checksum))
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
-						path, checksum, ondisk.checksum)));
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Restore a snapshot into 'builder' if previously one has been stored at the
+ * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ */
+static bool
+SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+{
+	SnapBuildOnDisk ondisk;
+	int			fd;
+	char		path[MAXPGPATH];
+
+	/* no point in loading a snapshot if we're already there */
+	if (builder->state == SNAPBUILD_CONSISTENT)
+		return false;
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		return false;
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+
+	/* validate and restore the snapshot to 'ondisk' */
+	ValidateAndRestoreSnapshotFile(&ondisk, path, fd, builder->context);
 
 	/*
 	 * ok, we now have a sensible snapshot here, figure out if it has more
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..3c1454df99 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -15,6 +15,10 @@
 #include "access/xlogdefs.h"
 #include "utils/snapmgr.h"
 
+/*
+ * Please keep get_snapbuild_state_desc() (located in the pg_logicalinspect
+ * module) updated if a change needs to be made to SnapBuildState.
+ */
 typedef enum
 {
 	/*
@@ -46,7 +50,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..c3919beb95
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,197 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+extern void ValidateAndRestoreSnapshotFile(SnapBuildOnDisk *ondisk, const char *path,
+										   int fd, MemoryContext context);
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
index 219afd6..71dea4a 100644
--- a/contrib/pg_logicalinspect/expected/logical_inspect.out
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -37,7 +37,7 @@ table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
 COMMIT                                                       
 (3 rows)
 
-step s1_get_logical_snapshot_info: SELECT info.state,info.catchange_count,array_length(info.catchange_xip,1) AS catchange_array_length,info.committed_count,array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
+step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip, 1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip, 1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
 state     |catchange_count|catchange_array_length|committed_count|committed_array_length
 ----------+---------------+----------------------+---------------+----------------------
 consistent|              0|                      |              2|                     2
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
index 7dc3cd7..0a4d268 100644
--- a/contrib/pg_logicalinspect/specs/logical_inspect.spec
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -29,6 +29,6 @@ setup { SET synchronous_commit=on; }
 step "s1_checkpoint" { CHECKPOINT; }
 step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
 step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
-step "s1_get_logical_snapshot_info" { SELECT info.state,info.catchange_count,array_length(info.catchange_xip,1) AS catchange_array_length,info.committed_count,array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip, 1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip, 1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
 
 permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 7a3b963..4b24718 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1691,7 +1691,6 @@ ValidateAndRestoreSnapshotFile(SnapBuildOnDisk *ondisk, const char *path, int fd
 							   MemoryContext context)
 {
 	pg_crc32c	checksum;
-	Size		sz;
 
 	/* ----
 	 * Make sure the snapshot had been stored safely to disk, that's normally
@@ -1731,7 +1730,7 @@ ValidateAndRestoreSnapshotFile(SnapBuildOnDisk *ondisk, const char *path, int fd
 	/* restore committed xacts information */
 	if (ondisk->builder.committed.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		Size sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
 		ondisk->builder.committed.xip = MemoryContextAllocZero(context, sz);
 		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
 		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
@@ -1740,7 +1739,7 @@ ValidateAndRestoreSnapshotFile(SnapBuildOnDisk *ondisk, const char *path, int fd
 	/* restore catalog modifying xacts information */
 	if (ondisk->builder.catchange.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		Size sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
 		ondisk->builder.catchange.xip = MemoryContextAllocZero(context, sz);
 		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
 		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
@@ -1782,13 +1781,15 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 
 	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
 
-	if (fd < 0 && errno == ENOENT)
-		return false;
-	else if (fd < 0)
+	if (fd < 0)
+	{
+		if (errno == ENOENT)
+			return false;
+
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not open file \"%s\": %m", path)));
-
+	}
 
 	/* validate and restore the snapshot to 'ondisk' */
 	ValidateAndRestoreSnapshotFile(&ondisk, path, fd, builder->context);

From ea6e205761038924ddfe541498890d45f438aafc Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v12] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 ++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 199 +++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 142 +++++++++
 src/backend/replication/logical/snapbuild.c   | 279 ++++--------------
 src/include/replication/snapbuild.h           |   6 +-
 src/include/replication/snapbuild_internal.h  | 199 +++++++++++++
 17 files changed, 817 insertions(+), 221 deletions(-)
   7.5% contrib/pg_logicalinspect/expected/
   5.3% contrib/pg_logicalinspect/specs/
  28.0% contrib/pg_logicalinspect/
  13.5% doc/src/sgml/
  25.1% src/backend/replication/logical/
  20.2% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..d95efa4d1e
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
+state     |catchange_count|catchange_array_length|committed_count|committed_array_length
+----------+---------------+----------------------+---------------+----------------------
+consistent|              0|                      |              2|                     2
+consistent|              2|                     2|              0|                      
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..3ec635509b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect logical decoding components',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..c773f6e458
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN filename text,
+    OUT magic int4,
+    OUT checksum int8,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN filename text,
+    OUT state text,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..0e3e1f50fc
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,199 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/* Return the description of SnapBuildState */
+static const char *
+get_snapbuild_state_desc(SnapBuildState state)
+{
+	const char *stateDesc = "unknown state";
+
+	switch (state)
+	{
+		case SNAPBUILD_START:
+			stateDesc = "start";
+			break;
+		case SNAPBUILD_BUILDING_SNAPSHOT:
+			stateDesc = "building";
+			break;
+		case SNAPBUILD_FULL_SNAPSHOT:
+			stateDesc = "full";
+			break;
+		case SNAPBUILD_CONSISTENT:
+			stateDesc = "consistent";
+			break;
+	}
+
+	return stateDesc;
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	MemoryContext context;
+	int			fd;
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	ValidateAndRestoreSnapshotFile(&ondisk, path, fd, context);
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = UInt32GetDatum(ondisk.magic);
+	values[i++] = Int64GetDatum((int64) ondisk.checksum);
+	values[i++] = UInt32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	MemoryContext context;
+	int			fd;
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+	context = AllocSetContextCreate(CurrentMemoryContext,
+									"logicalsnapshot inspect context",
+									ALLOCSET_DEFAULT_SIZES);
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	ValidateAndRestoreSnapshotFile(&ondisk, path, fd, context);
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = CStringGetTextDatum(get_snapbuild_state_desc(ondisk.builder.state));
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.committed.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.committed.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+		int			narrayelems = 0;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (; narrayelems < ondisk.builder.catchange.xcnt; narrayelems++)
+			arrayelems[narrayelems] = Int64GetDatum((int64) ondisk.builder.catchange.xip[narrayelems]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems, narrayelems, INT8OID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	MemoryContextReset(context);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..9851a6c18e
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+    CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+    DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
+step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..e984979462
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,142 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <para>
+  By default, use of these functions is restricted to superusers and members of
+  the <literal>pg_read_server_files</literal> role. Access may be granted by
+  superusers to others using <command>GRANT</command>.
+ </para>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0-40796E18.snap');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT meta.* FROM pg_ls_logicalsnapdir(),
+pg_get_logical_snapshot_meta(name) AS meta;
+
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0-40796E18.snap');
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT info.* FROM pg_ls_logicalsnapdir(),
+pg_get_logical_snapshot_info(name) AS info;
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..7a3b963a2f 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -1557,40 +1418,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
 #define SnapBuildOnDiskConstantSize \
 	offsetof(SnapBuildOnDisk, builder)
 #define SnapBuildOnDiskNotChecksummedSize \
@@ -1857,34 +1684,14 @@ out:
 }
 
 /*
- * Restore a snapshot into 'builder' if previously one has been stored at the
- * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ * Validate the logical snapshot file and read its contents to 'ondisk'.
  */
-static bool
-SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+void
+ValidateAndRestoreSnapshotFile(SnapBuildOnDisk *ondisk, const char *path, int fd,
+							   MemoryContext context)
 {
-	SnapBuildOnDisk ondisk;
-	int			fd;
-	char		path[MAXPGPATH];
-	Size		sz;
 	pg_crc32c	checksum;
-
-	/* no point in loading a snapshot if we're already there */
-	if (builder->state == SNAPBUILD_CONSISTENT)
-		return false;
-
-	sprintf(path, "%s/%X-%X.snap",
-			PG_LOGICAL_SNAPSHOTS_DIR,
-			LSN_FORMAT_ARGS(lsn));
-
-	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
-
-	if (fd < 0 && errno == ENOENT)
-		return false;
-	else if (fd < 0)
-		ereport(ERROR,
-				(errcode_for_file_access(),
-				 errmsg("could not open file \"%s\": %m", path)));
+	Size		sz;
 
 	/* ----
 	 * Make sure the snapshot had been stored safely to disk, that's normally
@@ -1897,47 +1704,46 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	fsync_fname(path, false);
 	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
 
-
 	/* read statically sized portion of snapshot */
-	SnapBuildRestoreContents(fd, (char *) &ondisk, SnapBuildOnDiskConstantSize, path);
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
 
-	if (ondisk.magic != SNAPBUILD_MAGIC)
+	if (ondisk->magic != SNAPBUILD_MAGIC)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
-						path, ondisk.magic, SNAPBUILD_MAGIC)));
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
 
-	if (ondisk.version != SNAPBUILD_VERSION)
+	if (ondisk->version != SNAPBUILD_VERSION)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
-						path, ondisk.version, SNAPBUILD_VERSION)));
+						path, ondisk->version, SNAPBUILD_VERSION)));
 
 	INIT_CRC32C(checksum);
 	COMP_CRC32C(checksum,
-				((char *) &ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
 				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
 
 	/* read SnapBuild */
-	SnapBuildRestoreContents(fd, (char *) &ondisk.builder, sizeof(SnapBuild), path);
-	COMP_CRC32C(checksum, &ondisk.builder, sizeof(SnapBuild));
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
 
 	/* restore committed xacts information */
-	if (ondisk.builder.committed.xcnt > 0)
+	if (ondisk->builder.committed.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.committed.xcnt;
-		ondisk.builder.committed.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.committed.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.committed.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
 	}
 
 	/* restore catalog modifying xacts information */
-	if (ondisk.builder.catchange.xcnt > 0)
+	if (ondisk->builder.catchange.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.catchange.xcnt;
-		ondisk.builder.catchange.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.catchange.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.catchange.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
 	}
 
 	if (CloseTransientFile(fd) != 0)
@@ -1948,11 +1754,44 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	FIN_CRC32C(checksum);
 
 	/* verify checksum of what we've read */
-	if (!EQ_CRC32C(checksum, ondisk.checksum))
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
-						path, checksum, ondisk.checksum)));
+						path, checksum, ondisk->checksum)));
+}
+
+/*
+ * Restore a snapshot into 'builder' if previously one has been stored at the
+ * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ */
+static bool
+SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+{
+	SnapBuildOnDisk ondisk;
+	int			fd;
+	char		path[MAXPGPATH];
+
+	/* no point in loading a snapshot if we're already there */
+	if (builder->state == SNAPBUILD_CONSISTENT)
+		return false;
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
+
+	if (fd < 0 && errno == ENOENT)
+		return false;
+	else if (fd < 0)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m", path)));
+
+
+	/* validate and restore the snapshot to 'ondisk' */
+	ValidateAndRestoreSnapshotFile(&ondisk, path, fd, builder->context);
 
 	/*
 	 * ok, we now have a sensible snapshot here, figure out if it has more
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..3c1454df99 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -15,6 +15,10 @@
 #include "access/xlogdefs.h"
 #include "utils/snapmgr.h"
 
+/*
+ * Please keep get_snapbuild_state_desc() (located in the pg_logicalinspect
+ * module) updated if a change needs to be made to SnapBuildState.
+ */
 typedef enum
 {
 	/*
@@ -46,7 +50,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..4791a90991
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,199 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ * Check if the SnapBuildOnDiskConstantSize and SnapBuildOnDiskNotChecksummedSize
+ * macros need to be updated when modifying the SnapBuildOnDisk struct.
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+extern void ValidateAndRestoreSnapshotFile(SnapBuildOnDisk *ondisk, const char *path,
+										   int fd, MemoryContext context);
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

From 6e43fffe9e2995c0183809550aadef505bf4693c Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Thu, 10 Oct 2024 04:09:53 +0000
Subject: [PATCH v13 1/2] Add XIDOID in [de]construct_array_builtin()

Using construct_array_builtin() for XIDOID is a new use case that is coming with
a new module (not added in the code tree yet).

d746021de1 (which introduced construct_array_builtin()) did not take care of
XIDOID because there were no use case at that time. Now that there is one, let's
add XIDOID.
---
 src/backend/utils/adt/arrayfuncs.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)
 100.0% src/backend/utils/adt/

diff --git a/src/backend/utils/adt/arrayfuncs.c b/src/backend/utils/adt/arrayfuncs.c
index e5c7e57a5d..8687fae359 100644
--- a/src/backend/utils/adt/arrayfuncs.c
+++ b/src/backend/utils/adt/arrayfuncs.c
@@ -3447,6 +3447,12 @@ construct_array_builtin(Datum *elems, int nelems, Oid elmtype)
 			elmalign = TYPALIGN_SHORT;
 			break;
 
+		case XIDOID:
+			elmlen = sizeof(TransactionId);
+			elmbyval = true;
+			elmalign = TYPALIGN_INT;
+			break;
+
 		default:
 			elog(ERROR, "type %u not supported by construct_array_builtin()", elmtype);
 			/* keep compiler quiet */
@@ -3734,6 +3740,12 @@ deconstruct_array_builtin(ArrayType *array,
 			elmalign = TYPALIGN_SHORT;
 			break;
 
+		case XIDOID:
+			elmlen = sizeof(TransactionId);
+			elmbyval = true;
+			elmalign = TYPALIGN_INT;
+			break;
+
 		default:
 			elog(ERROR, "type %u not supported by deconstruct_array_builtin()", elmtype);
 			/* keep compiler quiet */
-- 
2.34.1

From 16d4bc443371a80a4d2617750cfa8b0f22fd6a89 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v13 2/2] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   4 +
 contrib/pg_logicalinspect/Makefile            |  31 ++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 171 +++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 143 ++++++++++
 src/backend/replication/logical/snapbuild.c   | 270 ++++--------------
 src/include/replication/snapbuild.h           |   6 +-
 src/include/replication/snapbuild_internal.h  | 199 +++++++++++++
 17 files changed, 788 insertions(+), 214 deletions(-)
   7.7% contrib/pg_logicalinspect/expected/
   5.3% contrib/pg_logicalinspect/specs/
  26.1% contrib/pg_logicalinspect/
  14.0% doc/src/sgml/
  25.9% src/backend/replication/logical/
  20.6% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..5dcb3ff972
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,4 @@
+# Generated subdirectories
+/log/
+/results/
+/tmp_check/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..d95efa4d1e
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
+state     |catchange_count|catchange_array_length|committed_count|committed_array_length
+----------+---------------+----------------------+---------------+----------------------
+consistent|              0|                      |              2|                     2
+consistent|              2|                     2|              0|                      
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..3ec635509b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect logical decoding components',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..c773f6e458
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN filename text,
+    OUT magic int4,
+    OUT checksum int8,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN filename text,
+    OUT state text,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..a1c43f58cd
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,171 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/* Return the description of SnapBuildState */
+static const char *
+get_snapbuild_state_desc(SnapBuildState state)
+{
+	const char *stateDesc = "unknown state";
+
+	switch (state)
+	{
+		case SNAPBUILD_START:
+			stateDesc = "start";
+			break;
+		case SNAPBUILD_BUILDING_SNAPSHOT:
+			stateDesc = "building";
+			break;
+		case SNAPBUILD_FULL_SNAPSHOT:
+			stateDesc = "full";
+			break;
+		case SNAPBUILD_CONSISTENT:
+			stateDesc = "consistent";
+			break;
+	}
+
+	return stateDesc;
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	ValidateAndRestoreSnapshotFile(&ondisk, path, CurrentMemoryContext, false);
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = UInt32GetDatum(ondisk.magic);
+	values[i++] = Int64GetDatum((int64) ondisk.checksum);
+	values[i++] = UInt32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS];
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	ValidateAndRestoreSnapshotFile(&ondisk, path, CurrentMemoryContext, false);
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	memset(nulls, 0, sizeof(nulls));
+
+	values[i++] = CStringGetTextDatum(get_snapbuild_state_desc(ondisk.builder.state));
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (int j = 0; j < ondisk.builder.committed.xcnt; j++)
+			arrayelems[j] = TransactionIdGetDatum(ondisk.builder.committed.xip[j]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems,
+															  ondisk.builder.committed.xcnt,
+															  XIDOID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (int j = 0; j < ondisk.builder.catchange.xcnt; j++)
+			arrayelems[j] = TransactionIdGetDatum(ondisk.builder.catchange.xip[j]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems,
+															  ondisk.builder.catchange.xcnt,
+															  XIDOID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..9851a6c18e
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+    CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+    DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
+step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..e0fac997b6
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,143 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <para>
+  By default, use of these functions is restricted to superusers and members of
+  the <literal>pg_read_server_files</literal> role. Access may be granted by
+  superusers to others using <command>GRANT</command>.
+ </para>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0-40796E18.snap');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT ss.name, meta.* FROM pg_ls_logicalsnapdir() AS ss,
+pg_get_logical_snapshot_meta(ss.name) AS meta;
+-[ RECORD 1 ]-------------
+name     | 0-40796E18.snap
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0-40796E18.snap');
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT ss.name, info.* FROM pg_ls_logicalsnapdir() AS ss,
+pg_get_logical_snapshot_info(ss.name) AS info;
+-[ RECORD 1 ]------------+----------------
+name                     | 0-40796E18.snap
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..c197198b87 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -1557,40 +1418,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
 #define SnapBuildOnDiskConstantSize \
 	offsetof(SnapBuildOnDisk, builder)
 #define SnapBuildOnDiskNotChecksummedSize \
@@ -1857,34 +1684,27 @@ out:
 }
 
 /*
- * Restore a snapshot into 'builder' if previously one has been stored at the
- * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ * Validate the logical snapshot file and read its contents to 'ondisk'.
  */
-static bool
-SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+bool
+ValidateAndRestoreSnapshotFile(SnapBuildOnDisk *ondisk, const char *path,
+							   MemoryContext context, bool missing_ok)
 {
-	SnapBuildOnDisk ondisk;
 	int			fd;
-	char		path[MAXPGPATH];
-	Size		sz;
 	pg_crc32c	checksum;
-
-	/* no point in loading a snapshot if we're already there */
-	if (builder->state == SNAPBUILD_CONSISTENT)
-		return false;
-
-	sprintf(path, "%s/%X-%X.snap",
-			PG_LOGICAL_SNAPSHOTS_DIR,
-			LSN_FORMAT_ARGS(lsn));
+	Size		sz;
 
 	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
 
-	if (fd < 0 && errno == ENOENT)
-		return false;
-	else if (fd < 0)
+	if (fd < 0)
+	{
+		if (missing_ok && errno == ENOENT)
+			return false;
+
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not open file \"%s\": %m", path)));
+	}
 
 	/* ----
 	 * Make sure the snapshot had been stored safely to disk, that's normally
@@ -1897,47 +1717,46 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	fsync_fname(path, false);
 	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
 
-
 	/* read statically sized portion of snapshot */
-	SnapBuildRestoreContents(fd, (char *) &ondisk, SnapBuildOnDiskConstantSize, path);
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
 
-	if (ondisk.magic != SNAPBUILD_MAGIC)
+	if (ondisk->magic != SNAPBUILD_MAGIC)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
-						path, ondisk.magic, SNAPBUILD_MAGIC)));
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
 
-	if (ondisk.version != SNAPBUILD_VERSION)
+	if (ondisk->version != SNAPBUILD_VERSION)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
-						path, ondisk.version, SNAPBUILD_VERSION)));
+						path, ondisk->version, SNAPBUILD_VERSION)));
 
 	INIT_CRC32C(checksum);
 	COMP_CRC32C(checksum,
-				((char *) &ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
 				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
 
 	/* read SnapBuild */
-	SnapBuildRestoreContents(fd, (char *) &ondisk.builder, sizeof(SnapBuild), path);
-	COMP_CRC32C(checksum, &ondisk.builder, sizeof(SnapBuild));
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
 
 	/* restore committed xacts information */
-	if (ondisk.builder.committed.xcnt > 0)
+	if (ondisk->builder.committed.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.committed.xcnt;
-		ondisk.builder.committed.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.committed.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.committed.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
 	}
 
 	/* restore catalog modifying xacts information */
-	if (ondisk.builder.catchange.xcnt > 0)
+	if (ondisk->builder.catchange.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.catchange.xcnt;
-		ondisk.builder.catchange.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.catchange.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.catchange.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
 	}
 
 	if (CloseTransientFile(fd) != 0)
@@ -1948,11 +1767,36 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	FIN_CRC32C(checksum);
 
 	/* verify checksum of what we've read */
-	if (!EQ_CRC32C(checksum, ondisk.checksum))
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
-						path, checksum, ondisk.checksum)));
+						path, checksum, ondisk->checksum)));
+
+	return true;
+}
+
+/*
+ * Restore a snapshot into 'builder' if previously one has been stored at the
+ * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ */
+static bool
+SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+{
+	SnapBuildOnDisk ondisk;
+	char		path[MAXPGPATH];
+
+	/* no point in loading a snapshot if we're already there */
+	if (builder->state == SNAPBUILD_CONSISTENT)
+		return false;
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	/* validate and restore the snapshot to 'ondisk' */
+	if (!ValidateAndRestoreSnapshotFile(&ondisk, path, builder->context, true))
+		return false;
 
 	/*
 	 * ok, we now have a sensible snapshot here, figure out if it has more
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..3c1454df99 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -15,6 +15,10 @@
 #include "access/xlogdefs.h"
 #include "utils/snapmgr.h"
 
+/*
+ * Please keep get_snapbuild_state_desc() (located in the pg_logicalinspect
+ * module) updated if a change needs to be made to SnapBuildState.
+ */
 typedef enum
 {
 	/*
@@ -46,7 +50,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..ade75c94f1
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,199 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ * Check if the SnapBuildOnDiskConstantSize and SnapBuildOnDiskNotChecksummedSize
+ * macros need to be updated when modifying the SnapBuildOnDisk struct.
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+extern bool ValidateAndRestoreSnapshotFile(SnapBuildOnDisk *ondisk, const char *path,
+										   MemoryContext context, bool missing_ok);
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

From 306d1d446773cf5d151fd2faa3b30df451c3dc1d Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Thu, 10 Oct 2024 04:09:53 +0000
Subject: [PATCH v14 1/2] Add XIDOID in construct_array_builtin()

Using construct_array_builtin() for XIDOID is a new use case that is coming with
a new module (not added in the code tree yet).

d746021de1 (which introduced construct_array_builtin()) did not take care of
XIDOID because there was no use case at that time. Now that there is one, let's
add XIDOID.
---
 src/backend/utils/adt/arrayfuncs.c | 6 ++++++
 1 file changed, 6 insertions(+)
 100.0% src/backend/utils/adt/

diff --git a/src/backend/utils/adt/arrayfuncs.c b/src/backend/utils/adt/arrayfuncs.c
index e5c7e57a5d..41434279c5 100644
--- a/src/backend/utils/adt/arrayfuncs.c
+++ b/src/backend/utils/adt/arrayfuncs.c
@@ -3447,6 +3447,12 @@ construct_array_builtin(Datum *elems, int nelems, Oid elmtype)
 			elmalign = TYPALIGN_SHORT;
 			break;
 
+		case XIDOID:
+			elmlen = sizeof(TransactionId);
+			elmbyval = true;
+			elmalign = TYPALIGN_INT;
+			break;
+
 		default:
 			elog(ERROR, "type %u not supported by construct_array_builtin()", elmtype);
 			/* keep compiler quiet */
-- 
2.34.1

From 420616a91db9967901aaa09825b970f0775a3405 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 14 Aug 2024 08:46:05 +0000
Subject: [PATCH v14 2/2] Add contrib/pg_logicalinspect

Provides SQL functions that allow to inspect logical decoding components.

It currently allows to inspect the contents of serialized logical snapshots of
a running database cluster, which is useful for debugging or educational
purposes.
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   6 +
 contrib/pg_logicalinspect/Makefile            |  31 ++
 .../expected/logical_inspect.out              |  52 ++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 +++
 .../pg_logicalinspect--1.0.sql                |  43 +++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 167 +++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 +++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 143 +++++++++
 src/backend/replication/logical/snapbuild.c   | 274 ++++--------------
 src/include/replication/snapbuild.h           |   6 +-
 src/include/replication/snapbuild_internal.h  | 199 +++++++++++++
 17 files changed, 790 insertions(+), 214 deletions(-)
   7.6% contrib/pg_logicalinspect/expected/
   5.3% contrib/pg_logicalinspect/specs/
  26.0% contrib/pg_logicalinspect/
  14.0% doc/src/sgml/
  26.2% src/backend/replication/logical/
  20.5% src/include/replication/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..b4903eba65
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,6 @@
+# Generated subdirectories
+/log/
+/results/
+/output_iso/
+/tmp_check/
+/tmp_check_iso/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..d95efa4d1e
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
+state     |catchange_count|catchange_array_length|committed_count|committed_array_length
+----------+---------------+----------------------+---------------+----------------------
+consistent|              0|                      |              2|                     2
+consistent|              2|                     2|              0|                      
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..3ec635509b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect logical decoding components',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..c773f6e458
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN filename text,
+    OUT magic int4,
+    OUT checksum int8,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN filename text,
+    OUT state text,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int8,
+    OUT committed_xip xid[],
+    OUT catchange_count int8,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..fabfe2a10c
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,167 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/* Return the description of SnapBuildState */
+static const char *
+get_snapbuild_state_desc(SnapBuildState state)
+{
+	const char *stateDesc = "unknown state";
+
+	switch (state)
+	{
+		case SNAPBUILD_START:
+			stateDesc = "start";
+			break;
+		case SNAPBUILD_BUILDING_SNAPSHOT:
+			stateDesc = "building";
+			break;
+		case SNAPBUILD_FULL_SNAPSHOT:
+			stateDesc = "full";
+			break;
+		case SNAPBUILD_CONSISTENT:
+			stateDesc = "consistent";
+			break;
+	}
+
+	return stateDesc;
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS] = {0};
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS] = {0};
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	SnapBuildRestoreSnapshot(&ondisk, path, CurrentMemoryContext, false);
+
+	values[i++] = UInt32GetDatum(ondisk.magic);
+	values[i++] = Int64GetDatum((int64) ondisk.checksum);
+	values[i++] = UInt32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS] = {0};
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS] = {0};
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	SnapBuildRestoreSnapshot(&ondisk, path, CurrentMemoryContext, false);
+
+	values[i++] = CStringGetTextDatum(get_snapbuild_state_desc(ondisk.builder.state));
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+
+	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (int j = 0; j < ondisk.builder.committed.xcnt; j++)
+			arrayelems[j] = TransactionIdGetDatum(ondisk.builder.committed.xip[j]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems,
+															  ondisk.builder.committed.xcnt,
+															  XIDOID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (int j = 0; j < ondisk.builder.catchange.xcnt; j++)
+			arrayelems[j] = TransactionIdGetDatum(ondisk.builder.catchange.xip[j]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems,
+															  ondisk.builder.catchange.xcnt,
+															  XIDOID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..9851a6c18e
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+    CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+    DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
+step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..e0fac997b6
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,143 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <para>
+  By default, use of these functions is restricted to superusers and members of
+  the <literal>pg_read_server_files</literal> role. Access may be granted by
+  superusers to others using <command>GRANT</command>.
+ </para>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>General Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0-40796E18.snap');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT ss.name, meta.* FROM pg_ls_logicalsnapdir() AS ss,
+pg_get_logical_snapshot_meta(ss.name) AS meta;
+-[ RECORD 1 ]-------------
+name     | 0-40796E18.snap
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0-40796E18.snap');
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT ss.name, info.* FROM pg_ls_logicalsnapdir() AS ss,
+pg_get_logical_snapshot_info(ss.name) AS info;
+-[ RECORD 1 ]------------+----------------
+name                     | 0-40796E18.snap
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..92fd57b77e 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -1557,40 +1418,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
 #define SnapBuildOnDiskConstantSize \
 	offsetof(SnapBuildOnDisk, builder)
 #define SnapBuildOnDiskNotChecksummedSize \
@@ -1857,34 +1684,31 @@ out:
 }
 
 /*
- * Restore a snapshot into 'builder' if previously one has been stored at the
- * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ * Restore the logical snapshot file contents to 'ondisk'.
+ *
+ * If 'missing_ok' is true, will not throw an error if the file is not found.
+ * 'context' is the memory context where the catalog modifying/committed xid
+ * will live.
  */
-static bool
-SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+bool
+SnapBuildRestoreSnapshot(SnapBuildOnDisk *ondisk, const char *path,
+						 MemoryContext context, bool missing_ok)
 {
-	SnapBuildOnDisk ondisk;
 	int			fd;
-	char		path[MAXPGPATH];
-	Size		sz;
 	pg_crc32c	checksum;
-
-	/* no point in loading a snapshot if we're already there */
-	if (builder->state == SNAPBUILD_CONSISTENT)
-		return false;
-
-	sprintf(path, "%s/%X-%X.snap",
-			PG_LOGICAL_SNAPSHOTS_DIR,
-			LSN_FORMAT_ARGS(lsn));
+	Size		sz;
 
 	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
 
-	if (fd < 0 && errno == ENOENT)
-		return false;
-	else if (fd < 0)
+	if (fd < 0)
+	{
+		if (missing_ok && errno == ENOENT)
+			return false;
+
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not open file \"%s\": %m", path)));
+	}
 
 	/* ----
 	 * Make sure the snapshot had been stored safely to disk, that's normally
@@ -1897,47 +1721,46 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	fsync_fname(path, false);
 	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
 
-
 	/* read statically sized portion of snapshot */
-	SnapBuildRestoreContents(fd, (char *) &ondisk, SnapBuildOnDiskConstantSize, path);
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
 
-	if (ondisk.magic != SNAPBUILD_MAGIC)
+	if (ondisk->magic != SNAPBUILD_MAGIC)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
-						path, ondisk.magic, SNAPBUILD_MAGIC)));
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
 
-	if (ondisk.version != SNAPBUILD_VERSION)
+	if (ondisk->version != SNAPBUILD_VERSION)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
-						path, ondisk.version, SNAPBUILD_VERSION)));
+						path, ondisk->version, SNAPBUILD_VERSION)));
 
 	INIT_CRC32C(checksum);
 	COMP_CRC32C(checksum,
-				((char *) &ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
 				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
 
 	/* read SnapBuild */
-	SnapBuildRestoreContents(fd, (char *) &ondisk.builder, sizeof(SnapBuild), path);
-	COMP_CRC32C(checksum, &ondisk.builder, sizeof(SnapBuild));
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
 
 	/* restore committed xacts information */
-	if (ondisk.builder.committed.xcnt > 0)
+	if (ondisk->builder.committed.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.committed.xcnt;
-		ondisk.builder.committed.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.committed.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.committed.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
 	}
 
 	/* restore catalog modifying xacts information */
-	if (ondisk.builder.catchange.xcnt > 0)
+	if (ondisk->builder.catchange.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.catchange.xcnt;
-		ondisk.builder.catchange.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.catchange.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.catchange.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
 	}
 
 	if (CloseTransientFile(fd) != 0)
@@ -1948,11 +1771,36 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	FIN_CRC32C(checksum);
 
 	/* verify checksum of what we've read */
-	if (!EQ_CRC32C(checksum, ondisk.checksum))
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
-						path, checksum, ondisk.checksum)));
+						path, checksum, ondisk->checksum)));
+
+	return true;
+}
+
+/*
+ * Restore a snapshot into 'builder' if previously one has been stored at the
+ * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ */
+static bool
+SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+{
+	SnapBuildOnDisk ondisk;
+	char		path[MAXPGPATH];
+
+	/* no point in loading a snapshot if we're already there */
+	if (builder->state == SNAPBUILD_CONSISTENT)
+		return false;
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	/* validate and restore the snapshot to 'ondisk' */
+	if (!SnapBuildRestoreSnapshot(&ondisk, path, builder->context, true))
+		return false;
 
 	/*
 	 * ok, we now have a sensible snapshot here, figure out if it has more
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..3c1454df99 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -15,6 +15,10 @@
 #include "access/xlogdefs.h"
 #include "utils/snapmgr.h"
 
+/*
+ * Please keep get_snapbuild_state_desc() (located in the pg_logicalinspect
+ * module) updated if a change needs to be made to SnapBuildState.
+ */
 typedef enum
 {
 	/*
@@ -46,7 +50,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..7134b48b96
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,199 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ * Check if the SnapBuildOnDiskConstantSize and SnapBuildOnDiskNotChecksummedSize
+ * macros need to be updated when modifying the SnapBuildOnDisk struct.
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+extern bool SnapBuildRestoreSnapshot(SnapBuildOnDisk *ondisk, const char *path,
+									 MemoryContext context, bool missing_ok);
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

commit 483f5a402b6f650d02e8f8668bd50b17680f2805
Author: Masahiko Sawada <sawada.mshk@gmail.com>
Date:   Fri Oct 11 15:52:49 2024 -0700

    minor changes

diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
index c773f6e458..8f7f947cbb 100644
--- a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -31,9 +31,9 @@ CREATE FUNCTION pg_get_logical_snapshot_info(IN filename text,
     OUT in_slot_creation boolean,
     OUT last_serialized_snapshot pg_lsn,
     OUT next_phase_at xid,
-    OUT committed_count int8,
+    OUT committed_count int4,
     OUT committed_xip xid[],
-    OUT catchange_count int8,
+    OUT catchange_count int4,
     OUT catchange_xip xid[]
 )
 AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
index fabfe2a10c..790c64d6fa 100644
--- a/contrib/pg_logicalinspect/pg_logicalinspect.c
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -123,7 +123,7 @@ pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
 	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
 	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
 
-	values[i++] = Int64GetDatum(ondisk.builder.committed.xcnt);
+	values[i++] = UInt32GetDatum(ondisk.builder.committed.xcnt);
 	if (ondisk.builder.committed.xcnt > 0)
 	{
 		Datum	   *arrayelems;
@@ -140,7 +140,7 @@ pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
 	else
 		nulls[i++] = true;
 
-	values[i++] = Int64GetDatum(ondisk.builder.catchange.xcnt);
+	values[i++] = UInt32GetDatum(ondisk.builder.catchange.xcnt);
 	if (ondisk.builder.catchange.xcnt > 0)
 	{
 		Datum	   *arrayelems;
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
index e0fac997b6..4b111f9611 100644
--- a/doc/src/sgml/pglogicalinspect.sgml
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -22,7 +22,7 @@
  </para>
 
  <sect2 id="pglogicalinspect-funcs">
-  <title>General Functions</title>
+  <title>Functions</title>
 
   <variablelist>
    <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">

From 0c58f9984a3848e8b51f1438de32cfaa7e0db438 Mon Sep 17 00:00:00 2001
From: Masahiko Sawada <sawada.mshk@gmail.com>
Date: Fri, 11 Oct 2024 16:23:14 -0700
Subject: [PATCH v15 1/2] Move SnapBuild and SnapBuildOnDisk structs to
 snapshot_internal.h

This commit moves the definitions of the SnapBuild and SnapBuildOnDisk
structs, related to logical snapshots, to the snapshot_internal.h
file. This change allows external tools, such as
pg_logicalinspect (with an upcoming patch), to access and utilize the
contents of logical snapshots.

Author: Bertrand Drouvot
Reviewed-by: Amit Kapila, Shveta Malik, Peter Smith
Discussion: https://postgr.es/m/ZscuZ92uGh3wm4tW%40ip-10-97-1-34.eu-west-3.compute.internal
---
 src/backend/replication/logical/snapbuild.c  | 175 +----------------
 src/include/replication/snapbuild.h          |   2 +-
 src/include/replication/snapbuild_internal.h | 196 +++++++++++++++++++
 3 files changed, 198 insertions(+), 175 deletions(-)
 create mode 100644 src/include/replication/snapbuild_internal.h

diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..b9df8c0a02 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -1557,40 +1418,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
 #define SnapBuildOnDiskConstantSize \
 	offsetof(SnapBuildOnDisk, builder)
 #define SnapBuildOnDiskNotChecksummedSize \
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..dbb4bc2f4b 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -46,7 +46,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..03719ccf2a
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,196 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ * Check if the SnapBuildOnDiskConstantSize and SnapBuildOnDiskNotChecksummedSize
+ * macros need to be updated when modifying the SnapBuildOnDisk struct.
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.39.3

From 5f6bc116ef46d1e32a0728db3e3b91ba80729201 Mon Sep 17 00:00:00 2001
From: Masahiko Sawada <sawada.mshk@gmail.com>
Date: Fri, 11 Oct 2024 16:24:14 -0700
Subject: [PATCH v15 2/2] Add contrib/pg_logicalinspect.

This module provides SQL functions that allow to inspect logical
decoding components.

It currently allows to inspect the contents of serialized logical
snapshots of a running database cluster, which is useful for debugging
or educational purposes.

Author: Bertrand Drouvot
Reviewed-by: Amit Kapila, Shveta Malik, Peter Smith, Peter Eisentraut
Reviewed-by: David G. Johnston
Discussion: https://postgr.es/m/ZscuZ92uGh3wm4tW%40ip-10-97-1-34.eu-west-3.compute.internal
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   6 +
 contrib/pg_logicalinspect/Makefile            |  31 ++++
 .../expected/logical_inspect.out              |  52 ++++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 ++++
 .../pg_logicalinspect--1.0.sql                |  43 +++++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 167 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 ++++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 143 +++++++++++++++
 src/backend/replication/logical/snapbuild.c   |  99 +++++++----
 src/backend/utils/adt/arrayfuncs.c            |   6 +
 src/include/replication/snapbuild.h           |   4 +
 src/include/replication/snapbuild_internal.h  |   3 +
 18 files changed, 598 insertions(+), 39 deletions(-)
 create mode 100644 contrib/pg_logicalinspect/.gitignore
 create mode 100644 contrib/pg_logicalinspect/Makefile
 create mode 100644 contrib/pg_logicalinspect/expected/logical_inspect.out
 create mode 100644 contrib/pg_logicalinspect/logicalinspect.conf
 create mode 100644 contrib/pg_logicalinspect/meson.build
 create mode 100644 contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
 create mode 100644 contrib/pg_logicalinspect/pg_logicalinspect.c
 create mode 100644 contrib/pg_logicalinspect/pg_logicalinspect.control
 create mode 100644 contrib/pg_logicalinspect/specs/logical_inspect.spec
 create mode 100644 doc/src/sgml/pglogicalinspect.sgml

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..b4903eba65
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,6 @@
+# Generated subdirectories
+/log/
+/results/
+/output_iso/
+/tmp_check/
+/tmp_check_iso/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..d95efa4d1e
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
+state     |catchange_count|catchange_array_length|committed_count|committed_array_length
+----------+---------------+----------------------+---------------+----------------------
+consistent|              0|                      |              2|                     2
+consistent|              2|                     2|              0|                      
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..3ec635509b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect logical decoding components',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..8f7f947cbb
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN filename text,
+    OUT magic int4,
+    OUT checksum int8,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN filename text,
+    OUT state text,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int4,
+    OUT committed_xip xid[],
+    OUT catchange_count int4,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..790c64d6fa
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,167 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/* Return the description of SnapBuildState */
+static const char *
+get_snapbuild_state_desc(SnapBuildState state)
+{
+	const char *stateDesc = "unknown state";
+
+	switch (state)
+	{
+		case SNAPBUILD_START:
+			stateDesc = "start";
+			break;
+		case SNAPBUILD_BUILDING_SNAPSHOT:
+			stateDesc = "building";
+			break;
+		case SNAPBUILD_FULL_SNAPSHOT:
+			stateDesc = "full";
+			break;
+		case SNAPBUILD_CONSISTENT:
+			stateDesc = "consistent";
+			break;
+	}
+
+	return stateDesc;
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS] = {0};
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS] = {0};
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	SnapBuildRestoreSnapshot(&ondisk, path, CurrentMemoryContext, false);
+
+	values[i++] = UInt32GetDatum(ondisk.magic);
+	values[i++] = Int64GetDatum((int64) ondisk.checksum);
+	values[i++] = UInt32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS] = {0};
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS] = {0};
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	SnapBuildRestoreSnapshot(&ondisk, path, CurrentMemoryContext, false);
+
+	values[i++] = CStringGetTextDatum(get_snapbuild_state_desc(ondisk.builder.state));
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+
+	values[i++] = UInt32GetDatum(ondisk.builder.committed.xcnt);
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (int j = 0; j < ondisk.builder.committed.xcnt; j++)
+			arrayelems[j] = TransactionIdGetDatum(ondisk.builder.committed.xip[j]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems,
+															  ondisk.builder.committed.xcnt,
+															  XIDOID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = UInt32GetDatum(ondisk.builder.catchange.xcnt);
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (int j = 0; j < ondisk.builder.catchange.xcnt; j++)
+			arrayelems[j] = TransactionIdGetDatum(ondisk.builder.catchange.xip[j]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems,
+															  ondisk.builder.catchange.xcnt,
+															  XIDOID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..9851a6c18e
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+    CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+    DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
+step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..4b111f9611
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,143 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <para>
+  By default, use of these functions is restricted to superusers and members of
+  the <literal>pg_read_server_files</literal> role. Access may be granted by
+  superusers to others using <command>GRANT</command>.
+ </para>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0-40796E18.snap');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT ss.name, meta.* FROM pg_ls_logicalsnapdir() AS ss,
+pg_get_logical_snapshot_meta(ss.name) AS meta;
+-[ RECORD 1 ]-------------
+name     | 0-40796E18.snap
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0-40796E18.snap');
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT ss.name, info.* FROM pg_ls_logicalsnapdir() AS ss,
+pg_get_logical_snapshot_info(ss.name) AS info;
+-[ RECORD 1 ]------------+----------------
+name                     | 0-40796E18.snap
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b9df8c0a02..92fd57b77e 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1684,34 +1684,31 @@ out:
 }
 
 /*
- * Restore a snapshot into 'builder' if previously one has been stored at the
- * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ * Restore the logical snapshot file contents to 'ondisk'.
+ *
+ * If 'missing_ok' is true, will not throw an error if the file is not found.
+ * 'context' is the memory context where the catalog modifying/committed xid
+ * will live.
  */
-static bool
-SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+bool
+SnapBuildRestoreSnapshot(SnapBuildOnDisk *ondisk, const char *path,
+						 MemoryContext context, bool missing_ok)
 {
-	SnapBuildOnDisk ondisk;
 	int			fd;
-	char		path[MAXPGPATH];
-	Size		sz;
 	pg_crc32c	checksum;
-
-	/* no point in loading a snapshot if we're already there */
-	if (builder->state == SNAPBUILD_CONSISTENT)
-		return false;
-
-	sprintf(path, "%s/%X-%X.snap",
-			PG_LOGICAL_SNAPSHOTS_DIR,
-			LSN_FORMAT_ARGS(lsn));
+	Size		sz;
 
 	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
 
-	if (fd < 0 && errno == ENOENT)
-		return false;
-	else if (fd < 0)
+	if (fd < 0)
+	{
+		if (missing_ok && errno == ENOENT)
+			return false;
+
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not open file \"%s\": %m", path)));
+	}
 
 	/* ----
 	 * Make sure the snapshot had been stored safely to disk, that's normally
@@ -1724,47 +1721,46 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	fsync_fname(path, false);
 	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
 
-
 	/* read statically sized portion of snapshot */
-	SnapBuildRestoreContents(fd, (char *) &ondisk, SnapBuildOnDiskConstantSize, path);
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
 
-	if (ondisk.magic != SNAPBUILD_MAGIC)
+	if (ondisk->magic != SNAPBUILD_MAGIC)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
-						path, ondisk.magic, SNAPBUILD_MAGIC)));
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
 
-	if (ondisk.version != SNAPBUILD_VERSION)
+	if (ondisk->version != SNAPBUILD_VERSION)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
-						path, ondisk.version, SNAPBUILD_VERSION)));
+						path, ondisk->version, SNAPBUILD_VERSION)));
 
 	INIT_CRC32C(checksum);
 	COMP_CRC32C(checksum,
-				((char *) &ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
 				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
 
 	/* read SnapBuild */
-	SnapBuildRestoreContents(fd, (char *) &ondisk.builder, sizeof(SnapBuild), path);
-	COMP_CRC32C(checksum, &ondisk.builder, sizeof(SnapBuild));
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
 
 	/* restore committed xacts information */
-	if (ondisk.builder.committed.xcnt > 0)
+	if (ondisk->builder.committed.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.committed.xcnt;
-		ondisk.builder.committed.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.committed.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.committed.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
 	}
 
 	/* restore catalog modifying xacts information */
-	if (ondisk.builder.catchange.xcnt > 0)
+	if (ondisk->builder.catchange.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.catchange.xcnt;
-		ondisk.builder.catchange.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.catchange.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.catchange.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
 	}
 
 	if (CloseTransientFile(fd) != 0)
@@ -1775,11 +1771,36 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	FIN_CRC32C(checksum);
 
 	/* verify checksum of what we've read */
-	if (!EQ_CRC32C(checksum, ondisk.checksum))
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
-						path, checksum, ondisk.checksum)));
+						path, checksum, ondisk->checksum)));
+
+	return true;
+}
+
+/*
+ * Restore a snapshot into 'builder' if previously one has been stored at the
+ * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ */
+static bool
+SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+{
+	SnapBuildOnDisk ondisk;
+	char		path[MAXPGPATH];
+
+	/* no point in loading a snapshot if we're already there */
+	if (builder->state == SNAPBUILD_CONSISTENT)
+		return false;
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	/* validate and restore the snapshot to 'ondisk' */
+	if (!SnapBuildRestoreSnapshot(&ondisk, path, builder->context, true))
+		return false;
 
 	/*
 	 * ok, we now have a sensible snapshot here, figure out if it has more
diff --git a/src/backend/utils/adt/arrayfuncs.c b/src/backend/utils/adt/arrayfuncs.c
index e5c7e57a5d..41434279c5 100644
--- a/src/backend/utils/adt/arrayfuncs.c
+++ b/src/backend/utils/adt/arrayfuncs.c
@@ -3447,6 +3447,12 @@ construct_array_builtin(Datum *elems, int nelems, Oid elmtype)
 			elmalign = TYPALIGN_SHORT;
 			break;
 
+		case XIDOID:
+			elmlen = sizeof(TransactionId);
+			elmbyval = true;
+			elmalign = TYPALIGN_INT;
+			break;
+
 		default:
 			elog(ERROR, "type %u not supported by construct_array_builtin()", elmtype);
 			/* keep compiler quiet */
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index dbb4bc2f4b..3c1454df99 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -15,6 +15,10 @@
 #include "access/xlogdefs.h"
 #include "utils/snapmgr.h"
 
+/*
+ * Please keep get_snapbuild_state_desc() (located in the pg_logicalinspect
+ * module) updated if a change needs to be made to SnapBuildState.
+ */
 typedef enum
 {
 	/*
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
index 03719ccf2a..7134b48b96 100644
--- a/src/include/replication/snapbuild_internal.h
+++ b/src/include/replication/snapbuild_internal.h
@@ -193,4 +193,7 @@ typedef struct SnapBuildOnDisk
 	/* variable amount of TransactionIds follows */
 } SnapBuildOnDisk;
 
+extern bool SnapBuildRestoreSnapshot(SnapBuildOnDisk *ondisk, const char *path,
+									 MemoryContext context, bool missing_ok);
+
 #endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.39.3

From ef5997544afd9f414648e5ccae6c0d08c5ab66fa Mon Sep 17 00:00:00 2001
From: Masahiko Sawada <sawada.mshk@gmail.com>
Date: Fri, 11 Oct 2024 16:23:14 -0700
Subject: [PATCH v16 1/2] Move SnapBuild and SnapBuildOnDisk structs to
 snapshot_internal.h

This commit moves the definitions of the SnapBuild and SnapBuildOnDisk
structs, related to logical snapshots, to the snapshot_internal.h
file. This change allows external tools, such as
pg_logicalinspect (with an upcoming patch), to access and utilize the
contents of logical snapshots.

Author: Bertrand Drouvot
Reviewed-by: Amit Kapila, Shveta Malik, Peter Smith
Discussion: https://postgr.es/m/ZscuZ92uGh3wm4tW%40ip-10-97-1-34.eu-west-3.compute.internal
---
 src/backend/replication/logical/snapbuild.c  | 175 +----------------
 src/include/replication/snapbuild.h          |   2 +-
 src/include/replication/snapbuild_internal.h | 196 +++++++++++++++++++
 3 files changed, 198 insertions(+), 175 deletions(-)
  46.4% src/backend/replication/logical/
  53.5% src/include/replication/

diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0450f94ba8..b9df8c0a02 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -134,6 +134,7 @@
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
 #include "replication/snapbuild.h"
+#include "replication/snapbuild_internal.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/proc.h"
@@ -143,146 +144,6 @@
 #include "utils/memutils.h"
 #include "utils/snapmgr.h"
 #include "utils/snapshot.h"
-
-/*
- * This struct contains the current state of the snapshot building
- * machinery. Besides a forward declaration in the header, it is not exposed
- * to the public, so we can easily change its contents.
- */
-struct SnapBuild
-{
-	/* how far are we along building our first full snapshot */
-	SnapBuildState state;
-
-	/* private memory context used to allocate memory for this module. */
-	MemoryContext context;
-
-	/* all transactions < than this have committed/aborted */
-	TransactionId xmin;
-
-	/* all transactions >= than this are uncommitted */
-	TransactionId xmax;
-
-	/*
-	 * Don't replay commits from an LSN < this LSN. This can be set externally
-	 * but it will also be advanced (never retreat) from within snapbuild.c.
-	 */
-	XLogRecPtr	start_decoding_at;
-
-	/*
-	 * LSN at which two-phase decoding was enabled or LSN at which we found a
-	 * consistent point at the time of slot creation.
-	 *
-	 * The prepared transactions, that were skipped because previously
-	 * two-phase was not enabled or are not covered by initial snapshot, need
-	 * to be sent later along with commit prepared and they must be before
-	 * this point.
-	 */
-	XLogRecPtr	two_phase_at;
-
-	/*
-	 * Don't start decoding WAL until the "xl_running_xacts" information
-	 * indicates there are no running xids with an xid smaller than this.
-	 */
-	TransactionId initial_xmin_horizon;
-
-	/* Indicates if we are building full snapshot or just catalog one. */
-	bool		building_full_snapshot;
-
-	/*
-	 * Indicates if we are using the snapshot builder for the creation of a
-	 * logical replication slot. If it's true, the start point for decoding
-	 * changes is not determined yet. So we skip snapshot restores to properly
-	 * find the start point. See SnapBuildFindSnapshot() for details.
-	 */
-	bool		in_slot_creation;
-
-	/*
-	 * Snapshot that's valid to see the catalog state seen at this moment.
-	 */
-	Snapshot	snapshot;
-
-	/*
-	 * LSN of the last location we are sure a snapshot has been serialized to.
-	 */
-	XLogRecPtr	last_serialized_snapshot;
-
-	/*
-	 * The reorderbuffer we need to update with usable snapshots et al.
-	 */
-	ReorderBuffer *reorder;
-
-	/*
-	 * TransactionId at which the next phase of initial snapshot building will
-	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
-	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
-	 */
-	TransactionId next_phase_at;
-
-	/*
-	 * Array of transactions which could have catalog changes that committed
-	 * between xmin and xmax.
-	 */
-	struct
-	{
-		/* number of committed transactions */
-		size_t		xcnt;
-
-		/* available space for committed transactions */
-		size_t		xcnt_space;
-
-		/*
-		 * Until we reach a CONSISTENT state, we record commits of all
-		 * transactions, not just the catalog changing ones. Record when that
-		 * changes so we know we cannot export a snapshot safely anymore.
-		 */
-		bool		includes_all_transactions;
-
-		/*
-		 * Array of committed transactions that have modified the catalog.
-		 *
-		 * As this array is frequently modified we do *not* keep it in
-		 * xidComparator order. Instead we sort the array when building &
-		 * distributing a snapshot.
-		 *
-		 * TODO: It's unclear whether that reasoning has much merit. Every
-		 * time we add something here after becoming consistent will also
-		 * require distributing a snapshot. Storing them sorted would
-		 * potentially also make it easier to purge (but more complicated wrt
-		 * wraparound?). Should be improved if sorting while building the
-		 * snapshot shows up in profiles.
-		 */
-		TransactionId *xip;
-	}			committed;
-
-	/*
-	 * Array of transactions and subtransactions that had modified catalogs
-	 * and were running when the snapshot was serialized.
-	 *
-	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
-	 * if the transaction has changed the catalog. But it could happen that
-	 * the logical decoding decodes only the commit record of the transaction
-	 * after restoring the previously serialized snapshot in which case we
-	 * will miss adding the xid to the snapshot and end up looking at the
-	 * catalogs with the wrong snapshot.
-	 *
-	 * Now to avoid the above problem, we serialize the transactions that had
-	 * modified the catalogs and are still running at the time of snapshot
-	 * serialization. We fill this array while restoring the snapshot and then
-	 * refer it while decoding commit to ensure if the xact has modified the
-	 * catalog. We discard this array when all the xids in the list become old
-	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
-	 */
-	struct
-	{
-		/* number of transactions */
-		size_t		xcnt;
-
-		/* This array must be sorted in xidComparator order */
-		TransactionId *xip;
-	}			catchange;
-};
-
 /*
  * Starting a transaction -- which we need to do while exporting a snapshot --
  * removes knowledge about the previously used resowner, so we save it here.
@@ -1557,40 +1418,6 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	}
 }
 
-/* -----------------------------------
- * Snapshot serialization support
- * -----------------------------------
- */
-
-/*
- * We store current state of struct SnapBuild on disk in the following manner:
- *
- * struct SnapBuildOnDisk;
- * TransactionId * committed.xcnt; (*not xcnt_space*)
- * TransactionId * catchange.xcnt;
- *
- */
-typedef struct SnapBuildOnDisk
-{
-	/* first part of this struct needs to be version independent */
-
-	/* data not covered by checksum */
-	uint32		magic;
-	pg_crc32c	checksum;
-
-	/* data covered by checksum */
-
-	/* version, in case we want to support pg_upgrade */
-	uint32		version;
-	/* how large is the on disk data, excluding the constant sized part */
-	uint32		length;
-
-	/* version dependent part */
-	SnapBuild	builder;
-
-	/* variable amount of TransactionIds follows */
-} SnapBuildOnDisk;
-
 #define SnapBuildOnDiskConstantSize \
 	offsetof(SnapBuildOnDisk, builder)
 #define SnapBuildOnDiskNotChecksummedSize \
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index caa5113ff8..dbb4bc2f4b 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -46,7 +46,7 @@ typedef enum
 	SNAPBUILD_CONSISTENT = 2,
 } SnapBuildState;
 
-/* forward declare so we don't have to expose the struct to the public */
+/* forward declare so we don't have to include snapbuild_internal.h */
 struct SnapBuild;
 typedef struct SnapBuild SnapBuild;
 
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
new file mode 100644
index 0000000000..03719ccf2a
--- /dev/null
+++ b/src/include/replication/snapbuild_internal.h
@@ -0,0 +1,196 @@
+/*-------------------------------------------------------------------------
+ *
+ * snapbuild_internal.h
+ *    This file contains declarations for logical decoding utility
+ *    functions for internal use.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * src/include/replication/snapbuild_internal.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef SNAPBUILD_INTERNAL_H
+#define SNAPBUILD_INTERNAL_H
+
+#include "port/pg_crc32c.h"
+#include "replication/reorderbuffer.h"
+#include "replication/snapbuild.h"
+
+/*
+ * This struct contains the current state of the snapshot building
+ * machinery. It is exposed to the public, so pay attention when changing its
+ * contents.
+ */
+typedef struct SnapBuild
+{
+	/* how far are we along building our first full snapshot */
+	SnapBuildState state;
+
+	/* private memory context used to allocate memory for this module. */
+	MemoryContext context;
+
+	/* all transactions < than this have committed/aborted */
+	TransactionId xmin;
+
+	/* all transactions >= than this are uncommitted */
+	TransactionId xmax;
+
+	/*
+	 * Don't replay commits from an LSN < this LSN. This can be set externally
+	 * but it will also be advanced (never retreat) from within snapbuild.c.
+	 */
+	XLogRecPtr	start_decoding_at;
+
+	/*
+	 * LSN at which two-phase decoding was enabled or LSN at which we found a
+	 * consistent point at the time of slot creation.
+	 *
+	 * The prepared transactions, that were skipped because previously
+	 * two-phase was not enabled or are not covered by initial snapshot, need
+	 * to be sent later along with commit prepared and they must be before
+	 * this point.
+	 */
+	XLogRecPtr	two_phase_at;
+
+	/*
+	 * Don't start decoding WAL until the "xl_running_xacts" information
+	 * indicates there are no running xids with an xid smaller than this.
+	 */
+	TransactionId initial_xmin_horizon;
+
+	/* Indicates if we are building full snapshot or just catalog one. */
+	bool		building_full_snapshot;
+
+	/*
+	 * Indicates if we are using the snapshot builder for the creation of a
+	 * logical replication slot. If it's true, the start point for decoding
+	 * changes is not determined yet. So we skip snapshot restores to properly
+	 * find the start point. See SnapBuildFindSnapshot() for details.
+	 */
+	bool		in_slot_creation;
+
+	/*
+	 * Snapshot that's valid to see the catalog state seen at this moment.
+	 */
+	Snapshot	snapshot;
+
+	/*
+	 * LSN of the last location we are sure a snapshot has been serialized to.
+	 */
+	XLogRecPtr	last_serialized_snapshot;
+
+	/*
+	 * The reorderbuffer we need to update with usable snapshots et al.
+	 */
+	ReorderBuffer *reorder;
+
+	/*
+	 * TransactionId at which the next phase of initial snapshot building will
+	 * happen. InvalidTransactionId if not known (i.e. SNAPBUILD_START), or
+	 * when no next phase necessary (SNAPBUILD_CONSISTENT).
+	 */
+	TransactionId next_phase_at;
+
+	/*
+	 * Array of transactions which could have catalog changes that committed
+	 * between xmin and xmax.
+	 */
+	struct
+	{
+		/* number of committed transactions */
+		size_t		xcnt;
+
+		/* available space for committed transactions */
+		size_t		xcnt_space;
+
+		/*
+		 * Until we reach a CONSISTENT state, we record commits of all
+		 * transactions, not just the catalog changing ones. Record when that
+		 * changes so we know we cannot export a snapshot safely anymore.
+		 */
+		bool		includes_all_transactions;
+
+		/*
+		 * Array of committed transactions that have modified the catalog.
+		 *
+		 * As this array is frequently modified we do *not* keep it in
+		 * xidComparator order. Instead we sort the array when building &
+		 * distributing a snapshot.
+		 *
+		 * TODO: It's unclear whether that reasoning has much merit. Every
+		 * time we add something here after becoming consistent will also
+		 * require distributing a snapshot. Storing them sorted would
+		 * potentially also make it easier to purge (but more complicated wrt
+		 * wraparound?). Should be improved if sorting while building the
+		 * snapshot shows up in profiles.
+		 */
+		TransactionId *xip;
+	}			committed;
+
+	/*
+	 * Array of transactions and subtransactions that had modified catalogs
+	 * and were running when the snapshot was serialized.
+	 *
+	 * We normally rely on some WAL record types such as HEAP2_NEW_CID to know
+	 * if the transaction has changed the catalog. But it could happen that
+	 * the logical decoding decodes only the commit record of the transaction
+	 * after restoring the previously serialized snapshot in which case we
+	 * will miss adding the xid to the snapshot and end up looking at the
+	 * catalogs with the wrong snapshot.
+	 *
+	 * Now to avoid the above problem, we serialize the transactions that had
+	 * modified the catalogs and are still running at the time of snapshot
+	 * serialization. We fill this array while restoring the snapshot and then
+	 * refer it while decoding commit to ensure if the xact has modified the
+	 * catalog. We discard this array when all the xids in the list become old
+	 * enough to matter. See SnapBuildPurgeOlderTxn for details.
+	 */
+	struct
+	{
+		/* number of transactions */
+		size_t		xcnt;
+
+		/* This array must be sorted in xidComparator order */
+		TransactionId *xip;
+	}			catchange;
+} SnapBuild;
+
+/* -----------------------------------
+ * Snapshot serialization support
+ * -----------------------------------
+ */
+
+/*
+ * We store current state of struct SnapBuild on disk in the following manner:
+ *
+ * struct SnapBuildOnDisk;
+ * TransactionId * committed.xcnt; (*not xcnt_space*)
+ * TransactionId * catchange.xcnt;
+ *
+ * Check if the SnapBuildOnDiskConstantSize and SnapBuildOnDiskNotChecksummedSize
+ * macros need to be updated when modifying the SnapBuildOnDisk struct.
+ */
+typedef struct SnapBuildOnDisk
+{
+	/* first part of this struct needs to be version independent */
+
+	/* data not covered by checksum */
+	uint32		magic;
+	pg_crc32c	checksum;
+
+	/* data covered by checksum */
+
+	/* version, in case we want to support pg_upgrade */
+	uint32		version;
+	/* how large is the on disk data, excluding the constant sized part */
+	uint32		length;
+
+	/* version dependent part */
+	SnapBuild	builder;
+
+	/* variable amount of TransactionIds follows */
+} SnapBuildOnDisk;
+
+#endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

From 9f9e2ed520d0e9315dc16521f2f7d1e26fc50cb7 Mon Sep 17 00:00:00 2001
From: Masahiko Sawada <sawada.mshk@gmail.com>
Date: Fri, 11 Oct 2024 16:24:14 -0700
Subject: [PATCH v16 2/2] Add contrib/pg_logicalinspect.

This module provides SQL functions that allow to inspect logical
decoding components.

It currently allows to inspect the contents of serialized logical
snapshots of a running database cluster, which is useful for debugging
or educational purposes.

Author: Bertrand Drouvot
Reviewed-by: Amit Kapila, Shveta Malik, Peter Smith, Peter Eisentraut
Reviewed-by: David G. Johnston
Discussion: https://postgr.es/m/ZscuZ92uGh3wm4tW%40ip-10-97-1-34.eu-west-3.compute.internal
---
 contrib/Makefile                              |   1 +
 contrib/meson.build                           |   1 +
 contrib/pg_logicalinspect/.gitignore          |   6 +
 contrib/pg_logicalinspect/Makefile            |  31 ++++
 .../expected/logical_inspect.out              |  52 ++++++
 contrib/pg_logicalinspect/logicalinspect.conf |   1 +
 contrib/pg_logicalinspect/meson.build         |  39 ++++
 .../pg_logicalinspect--1.0.sql                |  43 +++++
 contrib/pg_logicalinspect/pg_logicalinspect.c | 167 ++++++++++++++++++
 .../pg_logicalinspect.control                 |   5 +
 .../specs/logical_inspect.spec                |  34 ++++
 doc/src/sgml/contrib.sgml                     |   1 +
 doc/src/sgml/filelist.sgml                    |   1 +
 doc/src/sgml/pglogicalinspect.sgml            | 143 +++++++++++++++
 src/backend/replication/logical/snapbuild.c   |  99 +++++++----
 src/backend/utils/adt/arrayfuncs.c            |   6 +
 src/include/replication/snapbuild.h           |   4 +
 src/include/replication/snapbuild_internal.h  |   3 +
 18 files changed, 598 insertions(+), 39 deletions(-)
  12.0% contrib/pg_logicalinspect/expected/
   8.4% contrib/pg_logicalinspect/specs/
  40.8% contrib/pg_logicalinspect/
  21.9% doc/src/sgml/
  14.5% src/backend/replication/logical/

diff --git a/contrib/Makefile b/contrib/Makefile
index abd780f277..952855d9b6 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -32,6 +32,7 @@ SUBDIRS = \
 		passwordcheck	\
 		pg_buffercache	\
 		pg_freespacemap \
+		pg_logicalinspect \
 		pg_prewarm	\
 		pg_stat_statements \
 		pg_surgery	\
diff --git a/contrib/meson.build b/contrib/meson.build
index 14a8906865..159ff41555 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -46,6 +46,7 @@ subdir('passwordcheck')
 subdir('pg_buffercache')
 subdir('pgcrypto')
 subdir('pg_freespacemap')
+subdir('pg_logicalinspect')
 subdir('pg_prewarm')
 subdir('pgrowlocks')
 subdir('pg_stat_statements')
diff --git a/contrib/pg_logicalinspect/.gitignore b/contrib/pg_logicalinspect/.gitignore
new file mode 100644
index 0000000000..b4903eba65
--- /dev/null
+++ b/contrib/pg_logicalinspect/.gitignore
@@ -0,0 +1,6 @@
+# Generated subdirectories
+/log/
+/results/
+/output_iso/
+/tmp_check/
+/tmp_check_iso/
diff --git a/contrib/pg_logicalinspect/Makefile b/contrib/pg_logicalinspect/Makefile
new file mode 100644
index 0000000000..55124514d4
--- /dev/null
+++ b/contrib/pg_logicalinspect/Makefile
@@ -0,0 +1,31 @@
+# contrib/pg_logicalinspect/Makefile
+
+MODULE_big = pg_logicalinspect
+OBJS = \
+	$(WIN32RES) \
+	pg_logicalinspect.o
+PGFILEDESC = "pg_logicalinspect - functions to inspect logical decoding components"
+
+EXTENSION = pg_logicalinspect
+DATA = pg_logicalinspect--1.0.sql
+
+EXTRA_INSTALL = contrib/test_decoding
+
+ISOLATION = logical_inspect
+
+ISOLATION_OPTS = --temp-config $(top_srcdir)/contrib/pg_logicalinspect/logicalinspect.conf
+
+# Disabled because these tests require "wal_level=logical", which
+# some installcheck users do not have (e.g. buildfarm clients).
+NO_INSTALLCHECK = 1
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_logicalinspect
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
new file mode 100644
index 0000000000..d95efa4d1e
--- /dev/null
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -0,0 +1,52 @@
+Parsed test spec with 2 sessions
+
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
+?column?
+--------
+init    
+(1 row)
+
+step s0_begin: BEGIN;
+step s0_savepoint: SAVEPOINT sp1;
+step s0_truncate: TRUNCATE tbl1;
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data
+----
+(0 rows)
+
+step s0_commit: COMMIT;
+step s0_begin: BEGIN;
+step s0_insert: INSERT INTO tbl1 VALUES (1);
+step s1_checkpoint: CHECKPOINT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                   
+---------------------------------------
+BEGIN                                  
+table public.tbl1: TRUNCATE: (no-flags)
+COMMIT                                 
+(3 rows)
+
+step s0_commit: COMMIT;
+step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
+data                                                         
+-------------------------------------------------------------
+BEGIN                                                        
+table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
+COMMIT                                                       
+(3 rows)
+
+step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
+state     |catchange_count|catchange_array_length|committed_count|committed_array_length
+----------+---------------+----------------------+---------------+----------------------
+consistent|              0|                      |              2|                     2
+consistent|              2|                     2|              0|                      
+(2 rows)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+count
+-----
+    2
+(1 row)
+
diff --git a/contrib/pg_logicalinspect/logicalinspect.conf b/contrib/pg_logicalinspect/logicalinspect.conf
new file mode 100644
index 0000000000..e3d257315f
--- /dev/null
+++ b/contrib/pg_logicalinspect/logicalinspect.conf
@@ -0,0 +1 @@
+wal_level = logical
diff --git a/contrib/pg_logicalinspect/meson.build b/contrib/pg_logicalinspect/meson.build
new file mode 100644
index 0000000000..3ec635509b
--- /dev/null
+++ b/contrib/pg_logicalinspect/meson.build
@@ -0,0 +1,39 @@
+# Copyright (c) 2024, PostgreSQL Global Development Group
+
+pg_logicalinspect_sources = files('pg_logicalinspect.c')
+
+if host_system == 'windows'
+  pg_logicalinspect_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+    '--NAME', 'pg_logicalinspect',
+    '--FILEDESC', 'pg_logicalinspect - functions to inspect logical decoding components',])
+endif
+
+pg_logicalinspect = shared_module('pg_logicalinspect',
+  pg_logicalinspect_sources,
+  kwargs: contrib_mod_args + {
+      'dependencies': contrib_mod_args['dependencies'],
+  },
+)
+contrib_targets += pg_logicalinspect
+
+install_data(
+  'pg_logicalinspect.control',
+  'pg_logicalinspect--1.0.sql',
+  kwargs: contrib_data_args,
+)
+
+tests += {
+  'name': 'pg_logicalinspect',
+  'sd': meson.current_source_dir(),
+  'bd': meson.current_build_dir(),
+  'isolation': {
+    'specs': [
+      'logical_inspect',
+    ],
+    'regress_args': [
+      '--temp-config', files('logicalinspect.conf'),
+    ],
+    # see above
+    'runningcheck': false,
+  },
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
new file mode 100644
index 0000000000..8f7f947cbb
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql
@@ -0,0 +1,43 @@
+/* contrib/pg_logicalinspect/pg_logicalinspect--1.0.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_logicalinspect" to load this file. \quit
+
+--
+-- pg_get_logical_snapshot_meta()
+--
+CREATE FUNCTION pg_get_logical_snapshot_meta(IN filename text,
+    OUT magic int4,
+    OUT checksum int8,
+    OUT version int4
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_meta'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_meta(text) TO pg_read_server_files;
+
+--
+-- pg_get_logical_snapshot_info()
+--
+CREATE FUNCTION pg_get_logical_snapshot_info(IN filename text,
+    OUT state text,
+    OUT xmin xid,
+    OUT xmax xid,
+    OUT start_decoding_at pg_lsn,
+    OUT two_phase_at pg_lsn,
+    OUT initial_xmin_horizon xid,
+    OUT building_full_snapshot boolean,
+    OUT in_slot_creation boolean,
+    OUT last_serialized_snapshot pg_lsn,
+    OUT next_phase_at xid,
+    OUT committed_count int4,
+    OUT committed_xip xid[],
+    OUT catchange_count int4,
+    OUT catchange_xip xid[]
+)
+AS 'MODULE_PATHNAME', 'pg_get_logical_snapshot_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+REVOKE EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) FROM PUBLIC;
+GRANT EXECUTE ON FUNCTION pg_get_logical_snapshot_info(text) TO pg_read_server_files;
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.c b/contrib/pg_logicalinspect/pg_logicalinspect.c
new file mode 100644
index 0000000000..675760e686
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.c
@@ -0,0 +1,167 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_logicalinspect.c
+ *		  Functions to inspect contents of PostgreSQL logical snapshots
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *		  contrib/pg_logicalinspect/pg_logicalinspect.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "funcapi.h"
+#include "replication/snapbuild_internal.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/pg_lsn.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_meta);
+PG_FUNCTION_INFO_V1(pg_get_logical_snapshot_info);
+
+/* Return the description of SnapBuildState */
+static const char *
+get_snapbuild_state_desc(SnapBuildState state)
+{
+	const char *stateDesc = "unknown state";
+
+	switch (state)
+	{
+		case SNAPBUILD_START:
+			stateDesc = "start";
+			break;
+		case SNAPBUILD_BUILDING_SNAPSHOT:
+			stateDesc = "building";
+			break;
+		case SNAPBUILD_FULL_SNAPSHOT:
+			stateDesc = "full";
+			break;
+		case SNAPBUILD_CONSISTENT:
+			stateDesc = "consistent";
+			break;
+	}
+
+	return stateDesc;
+}
+
+/*
+ * Retrieve the logical snapshot file metadata.
+ */
+Datum
+pg_get_logical_snapshot_meta(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_META_COLS 3
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_META_COLS] = {0};
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_META_COLS] = {0};
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	SnapBuildRestoreSnapshot(&ondisk, path, CurrentMemoryContext, false);
+
+	values[i++] = UInt32GetDatum(ondisk.magic);
+	values[i++] = Int64GetDatum((int64) ondisk.checksum);
+	values[i++] = UInt32GetDatum(ondisk.version);
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_META_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_META_COLS
+}
+
+Datum
+pg_get_logical_snapshot_info(PG_FUNCTION_ARGS)
+{
+#define PG_GET_LOGICAL_SNAPSHOT_INFO_COLS 14
+	SnapBuildOnDisk ondisk;
+	HeapTuple	tuple;
+	Datum		values[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS] = {0};
+	bool		nulls[PG_GET_LOGICAL_SNAPSHOT_INFO_COLS] = {0};
+	TupleDesc	tupdesc;
+	char		path[MAXPGPATH];
+	int			i = 0;
+	text	   *filename_t = PG_GETARG_TEXT_PP(0);
+
+	/* Build a tuple descriptor for our result type */
+	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+		elog(ERROR, "return type must be a row type");
+
+	sprintf(path, "%s/%s",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			text_to_cstring(filename_t));
+
+	/* Validate and restore the snapshot to 'ondisk' */
+	SnapBuildRestoreSnapshot(&ondisk, path, CurrentMemoryContext, false);
+
+	values[i++] = CStringGetTextDatum(get_snapbuild_state_desc(ondisk.builder.state));
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmin);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.xmax);
+	values[i++] = LSNGetDatum(ondisk.builder.start_decoding_at);
+	values[i++] = LSNGetDatum(ondisk.builder.two_phase_at);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.initial_xmin_horizon);
+	values[i++] = BoolGetDatum(ondisk.builder.building_full_snapshot);
+	values[i++] = BoolGetDatum(ondisk.builder.in_slot_creation);
+	values[i++] = LSNGetDatum(ondisk.builder.last_serialized_snapshot);
+	values[i++] = TransactionIdGetDatum(ondisk.builder.next_phase_at);
+
+	values[i++] = UInt32GetDatum(ondisk.builder.committed.xcnt);
+	if (ondisk.builder.committed.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.committed.xcnt * sizeof(Datum));
+
+		for (int j = 0; j < ondisk.builder.committed.xcnt; j++)
+			arrayelems[j] = TransactionIdGetDatum(ondisk.builder.committed.xip[j]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems,
+															  ondisk.builder.committed.xcnt,
+															  XIDOID));
+	}
+	else
+		nulls[i++] = true;
+
+	values[i++] = UInt32GetDatum(ondisk.builder.catchange.xcnt);
+	if (ondisk.builder.catchange.xcnt > 0)
+	{
+		Datum	   *arrayelems;
+
+		arrayelems = (Datum *) palloc(ondisk.builder.catchange.xcnt * sizeof(Datum));
+
+		for (int j = 0; j < ondisk.builder.catchange.xcnt; j++)
+			arrayelems[j] = TransactionIdGetDatum(ondisk.builder.catchange.xip[j]);
+
+		values[i++] = PointerGetDatum(construct_array_builtin(arrayelems,
+															  ondisk.builder.catchange.xcnt,
+															  XIDOID));
+	}
+	else
+		nulls[i++] = true;
+
+	Assert(i == PG_GET_LOGICAL_SNAPSHOT_INFO_COLS);
+
+	tuple = heap_form_tuple(tupdesc, values, nulls);
+
+	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
+
+#undef PG_GET_LOGICAL_SNAPSHOT_INFO_COLS
+}
diff --git a/contrib/pg_logicalinspect/pg_logicalinspect.control b/contrib/pg_logicalinspect/pg_logicalinspect.control
new file mode 100644
index 0000000000..b4a70e57ba
--- /dev/null
+++ b/contrib/pg_logicalinspect/pg_logicalinspect.control
@@ -0,0 +1,5 @@
+# pg_logicalinspect extension
+comment = 'functions to inspect logical decoding components'
+default_version = '1.0'
+module_pathname = '$libdir/pg_logicalinspect'
+relocatable = true
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
new file mode 100644
index 0000000000..9851a6c18e
--- /dev/null
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -0,0 +1,34 @@
+# Test the pg_logicalinspect functions: that needs some permutation to
+# ensure that we are creating multiple logical snapshots and that one of them
+# contains ongoing catalogs changes.
+setup
+{
+    DROP TABLE IF EXISTS tbl1;
+    CREATE TABLE tbl1 (val1 integer, val2 integer);
+    CREATE EXTENSION pg_logicalinspect;
+}
+
+teardown
+{
+    DROP TABLE tbl1;
+    SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
+    DROP EXTENSION pg_logicalinspect;
+}
+
+session "s0"
+setup { SET synchronous_commit=on; }
+step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding'); }
+step "s0_begin" { BEGIN; }
+step "s0_savepoint" { SAVEPOINT sp1; }
+step "s0_truncate" { TRUNCATE tbl1; }
+step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
+step "s0_commit" { COMMIT; }
+
+session "s1"
+setup { SET synchronous_commit=on; }
+step "s1_checkpoint" { CHECKPOINT; }
+step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
+step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index 44639a8dca..7c381949a5 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -154,6 +154,7 @@ CREATE EXTENSION <replaceable>extension_name</replaceable>;
  &pgbuffercache;
  &pgcrypto;
  &pgfreespacemap;
+ &pglogicalinspect;
  &pgprewarm;
  &pgrowlocks;
  &pgstatstatements;
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index a7ff5f8264..66e6dccd4c 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -143,6 +143,7 @@
 <!ENTITY pgbuffercache   SYSTEM "pgbuffercache.sgml">
 <!ENTITY pgcrypto        SYSTEM "pgcrypto.sgml">
 <!ENTITY pgfreespacemap  SYSTEM "pgfreespacemap.sgml">
+<!ENTITY pglogicalinspect  SYSTEM "pglogicalinspect.sgml">
 <!ENTITY pgprewarm       SYSTEM "pgprewarm.sgml">
 <!ENTITY pgrowlocks      SYSTEM "pgrowlocks.sgml">
 <!ENTITY pgstatstatements SYSTEM "pgstatstatements.sgml">
diff --git a/doc/src/sgml/pglogicalinspect.sgml b/doc/src/sgml/pglogicalinspect.sgml
new file mode 100644
index 0000000000..4b111f9611
--- /dev/null
+++ b/doc/src/sgml/pglogicalinspect.sgml
@@ -0,0 +1,143 @@
+<!-- doc/src/sgml/pglogicalinspect.sgml -->
+
+<sect1 id="pglogicalinspect" xreflabel="pg_logicalinspect">
+ <title>pg_logicalinspect &mdash; logical decoding components inspection</title>
+
+ <indexterm zone="pglogicalinspect">
+  <primary>pg_logicalinspect</primary>
+ </indexterm>
+
+ <para>
+  The <filename>pg_logicalinspect</filename> module provides SQL functions
+  that allow you to inspect the contents of logical decoding components. It
+  allows the inspection of serialized logical snapshots of a running
+  <productname>PostgreSQL</productname> database cluster, which is useful
+  for debugging or educational purposes.
+ </para>
+
+ <para>
+  By default, use of these functions is restricted to superusers and members of
+  the <literal>pg_read_server_files</literal> role. Access may be granted by
+  superusers to others using <command>GRANT</command>.
+ </para>
+
+ <sect2 id="pglogicalinspect-funcs">
+  <title>Functions</title>
+
+  <variablelist>
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-meta">
+    <term>
+     <function>pg_get_logical_snapshot_meta(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot metadata about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_meta('0-40796E18.snap');
+-[ RECORD 1 ]--------
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+
+postgres=# SELECT ss.name, meta.* FROM pg_ls_logicalsnapdir() AS ss,
+pg_get_logical_snapshot_meta(ss.name) AS meta;
+-[ RECORD 1 ]-------------
+name     | 0-40796E18.snap
+magic    | 1369563137
+checksum | 1028045905
+version  | 6
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+   <varlistentry id="pglogicalinspect-funcs-pg-get-logical-snapshot-info">
+    <term>
+     <function>pg_get_logical_snapshot_info(filename text) returns record</function>
+    </term>
+
+    <listitem>
+     <para>
+      Gets logical snapshot information about a snapshot file that is located in
+      the server's <filename>pg_logical/snapshots</filename> directory.
+      The <replaceable>filename</replaceable> argument represents the snapshot
+      file name.
+      For example:
+<screen>
+postgres=# SELECT * FROM pg_ls_logicalsnapdir();
+-[ RECORD 1 ]+-----------------------
+name         | 0-40796E18.snap
+size         | 152
+modification | 2024-08-14 16:36:32+00
+
+postgres=# SELECT * FROM pg_get_logical_snapshot_info('0-40796E18.snap');
+-[ RECORD 1 ]------------+-----------
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+
+postgres=# SELECT ss.name, info.* FROM pg_ls_logicalsnapdir() AS ss,
+pg_get_logical_snapshot_info(ss.name) AS info;
+-[ RECORD 1 ]------------+----------------
+name                     | 0-40796E18.snap
+state                    | consistent
+xmin                     | 751
+xmax                     | 751
+start_decoding_at        | 0/40796AF8
+two_phase_at             | 0/40796AF8
+initial_xmin_horizon     | 0
+building_full_snapshot   | f
+in_slot_creation         | f
+last_serialized_snapshot | 0/0
+next_phase_at            | 0
+committed_count          | 0
+committed_xip            |
+catchange_count          | 2
+catchange_xip            | {751,752}
+</screen>
+     </para>
+     <para>
+      If <replaceable>filename</replaceable> does not match a snapshot file, the
+      function raises an error.
+     </para>
+    </listitem>
+   </varlistentry>
+
+  </variablelist>
+ </sect2>
+
+ <sect2 id="pglogicalinspect-author">
+  <title>Author</title>
+
+  <para>
+   Bertrand Drouvot <email>bertranddrouvot.pg@gmail.com</email>
+  </para>
+ </sect2>
+
+</sect1>
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b9df8c0a02..a6a4da3266 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -1684,34 +1684,31 @@ out:
 }
 
 /*
- * Restore a snapshot into 'builder' if previously one has been stored at the
- * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ * Restore the logical snapshot file contents to 'ondisk'.
+ *
+ * 'context' is the memory context where the catalog modifying/committed xid
+ * will live.
+ * If 'missing_ok' is true, will not throw an error if the file is not found.
  */
-static bool
-SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+bool
+SnapBuildRestoreSnapshot(SnapBuildOnDisk *ondisk, const char *path,
+						 MemoryContext context, bool missing_ok)
 {
-	SnapBuildOnDisk ondisk;
 	int			fd;
-	char		path[MAXPGPATH];
-	Size		sz;
 	pg_crc32c	checksum;
-
-	/* no point in loading a snapshot if we're already there */
-	if (builder->state == SNAPBUILD_CONSISTENT)
-		return false;
-
-	sprintf(path, "%s/%X-%X.snap",
-			PG_LOGICAL_SNAPSHOTS_DIR,
-			LSN_FORMAT_ARGS(lsn));
+	Size		sz;
 
 	fd = OpenTransientFile(path, O_RDONLY | PG_BINARY);
 
-	if (fd < 0 && errno == ENOENT)
-		return false;
-	else if (fd < 0)
+	if (fd < 0)
+	{
+		if (missing_ok && errno == ENOENT)
+			return false;
+
 		ereport(ERROR,
 				(errcode_for_file_access(),
 				 errmsg("could not open file \"%s\": %m", path)));
+	}
 
 	/* ----
 	 * Make sure the snapshot had been stored safely to disk, that's normally
@@ -1724,47 +1721,46 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	fsync_fname(path, false);
 	fsync_fname(PG_LOGICAL_SNAPSHOTS_DIR, true);
 
-
 	/* read statically sized portion of snapshot */
-	SnapBuildRestoreContents(fd, (char *) &ondisk, SnapBuildOnDiskConstantSize, path);
+	SnapBuildRestoreContents(fd, (char *) ondisk, SnapBuildOnDiskConstantSize, path);
 
-	if (ondisk.magic != SNAPBUILD_MAGIC)
+	if (ondisk->magic != SNAPBUILD_MAGIC)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has wrong magic number: %u instead of %u",
-						path, ondisk.magic, SNAPBUILD_MAGIC)));
+						path, ondisk->magic, SNAPBUILD_MAGIC)));
 
-	if (ondisk.version != SNAPBUILD_VERSION)
+	if (ondisk->version != SNAPBUILD_VERSION)
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("snapbuild state file \"%s\" has unsupported version: %u instead of %u",
-						path, ondisk.version, SNAPBUILD_VERSION)));
+						path, ondisk->version, SNAPBUILD_VERSION)));
 
 	INIT_CRC32C(checksum);
 	COMP_CRC32C(checksum,
-				((char *) &ondisk) + SnapBuildOnDiskNotChecksummedSize,
+				((char *) ondisk) + SnapBuildOnDiskNotChecksummedSize,
 				SnapBuildOnDiskConstantSize - SnapBuildOnDiskNotChecksummedSize);
 
 	/* read SnapBuild */
-	SnapBuildRestoreContents(fd, (char *) &ondisk.builder, sizeof(SnapBuild), path);
-	COMP_CRC32C(checksum, &ondisk.builder, sizeof(SnapBuild));
+	SnapBuildRestoreContents(fd, (char *) &ondisk->builder, sizeof(SnapBuild), path);
+	COMP_CRC32C(checksum, &ondisk->builder, sizeof(SnapBuild));
 
 	/* restore committed xacts information */
-	if (ondisk.builder.committed.xcnt > 0)
+	if (ondisk->builder.committed.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.committed.xcnt;
-		ondisk.builder.committed.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.committed.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.committed.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.committed.xcnt;
+		ondisk->builder.committed.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.committed.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.committed.xip, sz);
 	}
 
 	/* restore catalog modifying xacts information */
-	if (ondisk.builder.catchange.xcnt > 0)
+	if (ondisk->builder.catchange.xcnt > 0)
 	{
-		sz = sizeof(TransactionId) * ondisk.builder.catchange.xcnt;
-		ondisk.builder.catchange.xip = MemoryContextAllocZero(builder->context, sz);
-		SnapBuildRestoreContents(fd, (char *) ondisk.builder.catchange.xip, sz, path);
-		COMP_CRC32C(checksum, ondisk.builder.catchange.xip, sz);
+		sz = sizeof(TransactionId) * ondisk->builder.catchange.xcnt;
+		ondisk->builder.catchange.xip = MemoryContextAllocZero(context, sz);
+		SnapBuildRestoreContents(fd, (char *) ondisk->builder.catchange.xip, sz, path);
+		COMP_CRC32C(checksum, ondisk->builder.catchange.xip, sz);
 	}
 
 	if (CloseTransientFile(fd) != 0)
@@ -1775,11 +1771,36 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
 	FIN_CRC32C(checksum);
 
 	/* verify checksum of what we've read */
-	if (!EQ_CRC32C(checksum, ondisk.checksum))
+	if (!EQ_CRC32C(checksum, ondisk->checksum))
 		ereport(ERROR,
 				(errcode(ERRCODE_DATA_CORRUPTED),
 				 errmsg("checksum mismatch for snapbuild state file \"%s\": is %u, should be %u",
-						path, checksum, ondisk.checksum)));
+						path, checksum, ondisk->checksum)));
+
+	return true;
+}
+
+/*
+ * Restore a snapshot into 'builder' if previously one has been stored at the
+ * location indicated by 'lsn'. Returns true if successful, false otherwise.
+ */
+static bool
+SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn)
+{
+	SnapBuildOnDisk ondisk;
+	char		path[MAXPGPATH];
+
+	/* no point in loading a snapshot if we're already there */
+	if (builder->state == SNAPBUILD_CONSISTENT)
+		return false;
+
+	sprintf(path, "%s/%X-%X.snap",
+			PG_LOGICAL_SNAPSHOTS_DIR,
+			LSN_FORMAT_ARGS(lsn));
+
+	/* validate and restore the snapshot to 'ondisk' */
+	if (!SnapBuildRestoreSnapshot(&ondisk, path, builder->context, true))
+		return false;
 
 	/*
 	 * ok, we now have a sensible snapshot here, figure out if it has more
diff --git a/src/backend/utils/adt/arrayfuncs.c b/src/backend/utils/adt/arrayfuncs.c
index e5c7e57a5d..41434279c5 100644
--- a/src/backend/utils/adt/arrayfuncs.c
+++ b/src/backend/utils/adt/arrayfuncs.c
@@ -3447,6 +3447,12 @@ construct_array_builtin(Datum *elems, int nelems, Oid elmtype)
 			elmalign = TYPALIGN_SHORT;
 			break;
 
+		case XIDOID:
+			elmlen = sizeof(TransactionId);
+			elmbyval = true;
+			elmalign = TYPALIGN_INT;
+			break;
+
 		default:
 			elog(ERROR, "type %u not supported by construct_array_builtin()", elmtype);
 			/* keep compiler quiet */
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index dbb4bc2f4b..3c1454df99 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -15,6 +15,10 @@
 #include "access/xlogdefs.h"
 #include "utils/snapmgr.h"
 
+/*
+ * Please keep get_snapbuild_state_desc() (located in the pg_logicalinspect
+ * module) updated if a change needs to be made to SnapBuildState.
+ */
 typedef enum
 {
 	/*
diff --git a/src/include/replication/snapbuild_internal.h b/src/include/replication/snapbuild_internal.h
index 03719ccf2a..7134b48b96 100644
--- a/src/include/replication/snapbuild_internal.h
+++ b/src/include/replication/snapbuild_internal.h
@@ -193,4 +193,7 @@ typedef struct SnapBuildOnDisk
 	/* variable amount of TransactionIds follows */
 } SnapBuildOnDisk;
 
+extern bool SnapBuildRestoreSnapshot(SnapBuildOnDisk *ondisk, const char *path,
+									 MemoryContext context, bool missing_ok);
+
 #endif							/* SNAPBUILD_INTERNAL_H */
-- 
2.34.1

From d590d3184d4345908f1b033aa8a5d19cf98e88ba Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 5 Mar 2025 07:06:58 +0000
Subject: [PATCH v1] Modify pg_logicalinspect isolation test

The previous version was relying on the fact that the test produces exactly
2 snapshots on disk, while in fact it can produce more. Changing the test knowing
that at least 2 snapshots are generated.

Per buildfarm member skink.
---
 .../expected/logical_inspect.out              | 29 +++++++++++--------
 .../specs/logical_inspect.spec                |  7 +++--
 2 files changed, 21 insertions(+), 15 deletions(-)
  57.3% contrib/pg_logicalinspect/expected/
  42.6% contrib/pg_logicalinspect/specs/

diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
index d95efa4d1e5..ecba05b9ab1 100644
--- a/contrib/pg_logicalinspect/expected/logical_inspect.out
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -1,6 +1,6 @@
 Parsed test spec with 2 sessions
 
-starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info_catchange s1_get_logical_snapshot_info_committed s1_get_logical_snapshot_meta
 step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
 ?column?
 --------
@@ -37,16 +37,21 @@ table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
 COMMIT                                                       
 (3 rows)
 
-step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
-state     |catchange_count|catchange_array_length|committed_count|committed_array_length
-----------+---------------+----------------------+---------------+----------------------
-consistent|              0|                      |              2|                     2
-consistent|              2|                     2|              0|                      
-(2 rows)
-
-step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
-count
------
-    2
+step s1_get_logical_snapshot_info_catchange: SELECT count(*) > 0 as has_catchange FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.catchange_count = 2 and array_length(info.catchange_xip,1) = 2 and info.committed_count = 0;
+has_catchange
+-------------
+t            
+(1 row)
+
+step s1_get_logical_snapshot_info_committed: SELECT count(*) > 0 as has_committed FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.committed_count = 2 and array_length(info.committed_xip,1) = 2 and info.catchange_count = 0;
+has_committed
+-------------
+t            
+(1 row)
+
+step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) > 1 AS has_meta from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+has_meta
+--------
+t       
 (1 row)
 
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
index 9851a6c18e4..673d2f5ed0a 100644
--- a/contrib/pg_logicalinspect/specs/logical_inspect.spec
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -28,7 +28,8 @@ session "s1"
 setup { SET synchronous_commit=on; }
 step "s1_checkpoint" { CHECKPOINT; }
 step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
-step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
-step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) > 1 AS has_meta from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta; }
+step "s1_get_logical_snapshot_info_catchange" { SELECT count(*) > 0 as has_catchange FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.catchange_count = 2 and array_length(info.catchange_xip,1) = 2 and info.committed_count = 0; }
+step "s1_get_logical_snapshot_info_committed" { SELECT count(*) > 0 as has_committed FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.committed_count = 2 and array_length(info.committed_xip,1) = 2 and info.catchange_count = 0; }
 
-permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info_catchange" "s1_get_logical_snapshot_info_committed" "s1_get_logical_snapshot_meta"
-- 
2.34.1

From 6154e847e4e5c2c7eb816d4302a4704d5a690954 Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 5 Mar 2025 07:06:58 +0000
Subject: [PATCH v2] Modify pg_logicalinspect isolation test

The previous version was relying on the fact that the test produces exactly
2 snapshots on disk, while in fact it can produce more. Changing the test knowing
that at least 2 snapshots are generated.

In passing, removing useless steps and adding some comments.

Per buildfarm member skink.
---
 .../expected/logical_inspect.out              | 36 ++++++++-----------
 .../specs/logical_inspect.spec                | 11 +++---
 2 files changed, 22 insertions(+), 25 deletions(-)
  58.4% contrib/pg_logicalinspect/expected/
  41.5% contrib/pg_logicalinspect/specs/

diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
index d95efa4d1e5..b7d01dbb68b 100644
--- a/contrib/pg_logicalinspect/expected/logical_inspect.out
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -1,6 +1,6 @@
 Parsed test spec with 2 sessions
 
-starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s1_checkpoint s1_get_changes s1_get_logical_snapshot_info_catchange s1_get_logical_snapshot_info_committed s1_get_logical_snapshot_meta
 step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
 ?column?
 --------
@@ -17,8 +17,6 @@ data
 (0 rows)
 
 step s0_commit: COMMIT;
-step s0_begin: BEGIN;
-step s0_insert: INSERT INTO tbl1 VALUES (1);
 step s1_checkpoint: CHECKPOINT;
 step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
 data                                   
@@ -28,25 +26,21 @@ table public.tbl1: TRUNCATE: (no-flags)
 COMMIT                                 
 (3 rows)
 
-step s0_commit: COMMIT;
-step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
-data                                                         
--------------------------------------------------------------
-BEGIN                                                        
-table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
-COMMIT                                                       
-(3 rows)
+step s1_get_logical_snapshot_info_catchange: SELECT count(*) > 0 as has_catchange FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.catchange_count = 2 and array_length(info.catchange_xip,1) = 2 and info.committed_count = 0;
+has_catchange
+-------------
+t            
+(1 row)
 
-step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
-state     |catchange_count|catchange_array_length|committed_count|committed_array_length
-----------+---------------+----------------------+---------------+----------------------
-consistent|              0|                      |              2|                     2
-consistent|              2|                     2|              0|                      
-(2 rows)
+step s1_get_logical_snapshot_info_committed: SELECT count(*) > 0 as has_committed FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.committed_count = 2 and array_length(info.committed_xip,1) = 2 and info.catchange_count = 0;
+has_committed
+-------------
+t            
+(1 row)
 
-step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
-count
------
-    2
+step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) > 1 AS has_meta from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+has_meta
+--------
+t       
 (1 row)
 
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
index 9851a6c18e4..631daf5db6c 100644
--- a/contrib/pg_logicalinspect/specs/logical_inspect.spec
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -21,14 +21,17 @@ step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolatio
 step "s0_begin" { BEGIN; }
 step "s0_savepoint" { SAVEPOINT sp1; }
 step "s0_truncate" { TRUNCATE tbl1; }
-step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
 step "s0_commit" { COMMIT; }
 
 session "s1"
 setup { SET synchronous_commit=on; }
 step "s1_checkpoint" { CHECKPOINT; }
 step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
-step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
-step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) > 1 AS has_meta from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta; }
+step "s1_get_logical_snapshot_info_catchange" { SELECT count(*) > 0 as has_catchange FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.catchange_count = 2 and array_length(info.catchange_xip,1) = 2 and info.committed_count = 0; }
+step "s1_get_logical_snapshot_info_committed" { SELECT count(*) > 0 as has_committed FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.committed_count = 2 and array_length(info.committed_xip,1) = 2 and info.catchange_count = 0; }
 
-permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
+# The first get_changes produces (at least) one snapshot that contains 2 catchanges
+# (the truncate and its parent transaction). The second get_changes produces one
+# snapshot that contains the 2 transactions above as committed.
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_checkpoint" "s1_get_changes" "s1_get_logical_snapshot_info_catchange" "s1_get_logical_snapshot_info_committed" "s1_get_logical_snapshot_meta"
-- 
2.34.1

From 415d707187070df88e11e9bb1059309ab102953e Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 5 Mar 2025 07:06:58 +0000
Subject: [PATCH v3] Modify pg_logicalinspect isolation test

The previous version was relying on the fact that the test produces exactly
2 snapshots on disk, while in fact it can produce more. Changing the test knowing
that at least 2 snapshots are generated.

In passing, removing useless steps and adding some comments.

Per buildfarm member skink.
---
 .../expected/logical_inspect.out              | 44 +++++--------------
 .../specs/logical_inspect.spec                | 18 +++++---
 2 files changed, 24 insertions(+), 38 deletions(-)
  57.1% contrib/pg_logicalinspect/expected/
  42.8% contrib/pg_logicalinspect/specs/

diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
index d95efa4d1e5..c86711e471d 100644
--- a/contrib/pg_logicalinspect/expected/logical_inspect.out
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -1,6 +1,6 @@
 Parsed test spec with 2 sessions
 
-starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_create_table s1_checkpoint s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta s0_commit
 step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
 ?column?
 --------
@@ -10,43 +10,23 @@ init
 step s0_begin: BEGIN;
 step s0_savepoint: SAVEPOINT sp1;
 step s0_truncate: TRUNCATE tbl1;
+step s1_create_table: CREATE TABLE tbl2 (val1 integer, val2 integer);
 step s1_checkpoint: CHECKPOINT;
 step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
 data
 ----
 (0 rows)
 
-step s0_commit: COMMIT;
-step s0_begin: BEGIN;
-step s0_insert: INSERT INTO tbl1 VALUES (1);
-step s1_checkpoint: CHECKPOINT;
-step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
-data                                   
----------------------------------------
-BEGIN                                  
-table public.tbl1: TRUNCATE: (no-flags)
-COMMIT                                 
-(3 rows)
-
-step s0_commit: COMMIT;
-step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
-data                                                         
--------------------------------------------------------------
-BEGIN                                                        
-table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
-COMMIT                                                       
-(3 rows)
-
-step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
-state     |catchange_count|catchange_array_length|committed_count|committed_array_length
-----------+---------------+----------------------+---------------+----------------------
-consistent|              0|                      |              2|                     2
-consistent|              2|                     2|              0|                      
-(2 rows)
+step s1_get_logical_snapshot_info: SELECT count(*) > 0 as has_info FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.catchange_count >= 2 and array_length(info.catchange_xip,1) >= 2 and info.committed_count >= 1 and array_length(info.committed_xip,1) >= 1;
+has_info
+--------
+t       
+(1 row)
 
-step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
-count
------
-    2
+step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) > 0 AS has_meta from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+has_meta
+--------
+t       
 (1 row)
 
+step s0_commit: COMMIT;
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
index 9851a6c18e4..a6bc58ae955 100644
--- a/contrib/pg_logicalinspect/specs/logical_inspect.spec
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -1,6 +1,6 @@
 # Test the pg_logicalinspect functions: that needs some permutation to
-# ensure that we are creating multiple logical snapshots and that one of them
-# contains ongoing catalogs changes.
+# ensure that we are creating at least one snapshot that contains ongoing and
+# committed catalogs changes.
 setup
 {
     DROP TABLE IF EXISTS tbl1;
@@ -11,6 +11,7 @@ setup
 teardown
 {
     DROP TABLE tbl1;
+    DROP TABLE tbl2;
     SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
     DROP EXTENSION pg_logicalinspect;
 }
@@ -21,14 +22,19 @@ step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolatio
 step "s0_begin" { BEGIN; }
 step "s0_savepoint" { SAVEPOINT sp1; }
 step "s0_truncate" { TRUNCATE tbl1; }
-step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
 step "s0_commit" { COMMIT; }
 
 session "s1"
 setup { SET synchronous_commit=on; }
 step "s1_checkpoint" { CHECKPOINT; }
+step "s1_create_table" { CREATE TABLE tbl2 (val1 integer, val2 integer); }
 step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
-step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
-step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) > 0 AS has_meta from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta; }
+step "s1_get_logical_snapshot_info" { SELECT count(*) > 0 as has_info FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.catchange_count >= 2 and array_length(info.catchange_xip,1) >= 2 and info.committed_count >= 1 and array_length(info.committed_xip,1) >= 1; }
 
-permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
+# s0 does not commit until the end of the test. This is needed to ensure that
+# a checkpoint will not remove any snapshots. s0 produces 2 ongoing catalog changes
+# (the truncate and its parent transaction). s1 produces a committed catalog change.
+# So that the get_changes produces (at least) one snapshot that contains 2
+# ongoing catalog changes and the committed catalog change.
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_create_table" "s1_checkpoint" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta" "s0_commit"
-- 
2.34.1

From c15a40c256e19c462e5e0ee8fdf868af25fa4fae Mon Sep 17 00:00:00 2001
From: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Date: Wed, 5 Mar 2025 07:06:58 +0000
Subject: [PATCH v4] pg_logicalinspect: Stabilize isolation tests.

The previous isolation tests did not account for the possibility that
the background writer or the checkpointer could write a RUNNING_XACTS
record, which could cause logical decoding to produce more logical
snapshots than expected.

This commit modifies the isolation tests to verify that at least one
logical snapshot contains the expected number of committed or ongoing
catalog-change transactions.

Per buildfarm member skink.

Reported-by: Andres Freund <andres@anarazel.de>
Author: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reviewed-by: Amit Kapila <amit.kapila16@gmail.com>
Reviewed-by: Masahiko Sawada <sawada.mshk@gmail.com>
Discussion: https://postgr.es/m/5qbxud4pvnvmtuoi7weiizm5hmumxaeohx4vztfhrwlfhyz6rj@buh4435mllwo
---
 .../expected/logical_inspect.out              | 44 +++++--------------
 .../specs/logical_inspect.spec                | 24 +++++++---
 2 files changed, 30 insertions(+), 38 deletions(-)

diff --git a/contrib/pg_logicalinspect/expected/logical_inspect.out b/contrib/pg_logicalinspect/expected/logical_inspect.out
index d95efa4d1e5..b343d3ad733 100644
--- a/contrib/pg_logicalinspect/expected/logical_inspect.out
+++ b/contrib/pg_logicalinspect/expected/logical_inspect.out
@@ -1,6 +1,6 @@
 Parsed test spec with 2 sessions
 
-starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_checkpoint s1_get_changes s0_commit s0_begin s0_insert s1_checkpoint s1_get_changes s0_commit s1_get_changes s1_get_logical_snapshot_info s1_get_logical_snapshot_meta
+starting permutation: s0_init s0_begin s0_savepoint s0_truncate s1_create_table s1_checkpoint s1_get_changes s1_check_snapshot_info s1_check_snapshot_meta s0_commit
 step s0_init: SELECT 'init' FROM pg_create_logical_replication_slot('isolation_slot', 'test_decoding');
 ?column?
 --------
@@ -10,43 +10,23 @@ init
 step s0_begin: BEGIN;
 step s0_savepoint: SAVEPOINT sp1;
 step s0_truncate: TRUNCATE tbl1;
+step s1_create_table: CREATE TABLE tbl2 (val1 integer, val2 integer);
 step s1_checkpoint: CHECKPOINT;
 step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
 data
 ----
 (0 rows)
 
-step s0_commit: COMMIT;
-step s0_begin: BEGIN;
-step s0_insert: INSERT INTO tbl1 VALUES (1);
-step s1_checkpoint: CHECKPOINT;
-step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
-data                                   
----------------------------------------
-BEGIN                                  
-table public.tbl1: TRUNCATE: (no-flags)
-COMMIT                                 
-(3 rows)
-
-step s0_commit: COMMIT;
-step s1_get_changes: SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0');
-data                                                         
--------------------------------------------------------------
-BEGIN                                                        
-table public.tbl1: INSERT: val1[integer]:1 val2[integer]:null
-COMMIT                                                       
-(3 rows)
-
-step s1_get_logical_snapshot_info: SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2;
-state     |catchange_count|catchange_array_length|committed_count|committed_array_length
-----------+---------------+----------------------+---------------+----------------------
-consistent|              0|                      |              2|                     2
-consistent|              2|                     2|              0|                      
-(2 rows)
+step s1_check_snapshot_info: SELECT count(*) > 0 as has_info FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.catchange_count >= 2 and array_length(info.catchange_xip,1) >= 2 and info.committed_count >= 1 and array_length(info.committed_xip,1) >= 1;
+has_info
+--------
+t       
+(1 row)
 
-step s1_get_logical_snapshot_meta: SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
-count
------
-    2
+step s1_check_snapshot_meta: SELECT count(meta.*) > 0 AS has_meta from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;
+has_meta
+--------
+t       
 (1 row)
 
+step s0_commit: COMMIT;
diff --git a/contrib/pg_logicalinspect/specs/logical_inspect.spec b/contrib/pg_logicalinspect/specs/logical_inspect.spec
index 9851a6c18e4..26b2db10f3e 100644
--- a/contrib/pg_logicalinspect/specs/logical_inspect.spec
+++ b/contrib/pg_logicalinspect/specs/logical_inspect.spec
@@ -1,9 +1,10 @@
 # Test the pg_logicalinspect functions: that needs some permutation to
-# ensure that we are creating multiple logical snapshots and that one of them
-# contains ongoing catalogs changes.
+# ensure that we are creating at least one snapshot that contains ongoing and
+# committed catalogs changes.
 setup
 {
     DROP TABLE IF EXISTS tbl1;
+    DROP TABLE IF EXISTS tbl2;
     CREATE TABLE tbl1 (val1 integer, val2 integer);
     CREATE EXTENSION pg_logicalinspect;
 }
@@ -11,6 +12,7 @@ setup
 teardown
 {
     DROP TABLE tbl1;
+    DROP TABLE tbl2;
     SELECT 'stop' FROM pg_drop_replication_slot('isolation_slot');
     DROP EXTENSION pg_logicalinspect;
 }
@@ -21,14 +23,24 @@ step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('isolatio
 step "s0_begin" { BEGIN; }
 step "s0_savepoint" { SAVEPOINT sp1; }
 step "s0_truncate" { TRUNCATE tbl1; }
-step "s0_insert" { INSERT INTO tbl1 VALUES (1); }
 step "s0_commit" { COMMIT; }
 
 session "s1"
 setup { SET synchronous_commit=on; }
 step "s1_checkpoint" { CHECKPOINT; }
+step "s1_create_table" { CREATE TABLE tbl2 (val1 integer, val2 integer); }
 step "s1_get_changes" { SELECT data FROM pg_logical_slot_get_changes('isolation_slot', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
-step "s1_get_logical_snapshot_meta" { SELECT COUNT(meta.*) from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta;}
-step "s1_get_logical_snapshot_info" { SELECT info.state, info.catchange_count, array_length(info.catchange_xip,1) AS catchange_array_length, info.committed_count, array_length(info.committed_xip,1) AS committed_array_length FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info ORDER BY 2; }
+step "s1_check_snapshot_meta" { SELECT count(meta.*) > 0 AS has_meta from pg_ls_logicalsnapdir(), pg_get_logical_snapshot_meta(name) as meta; }
+step "s1_check_snapshot_info" { SELECT count(*) > 0 as has_info FROM pg_ls_logicalsnapdir(), pg_get_logical_snapshot_info(name) AS info where info.catchange_count >= 2 and array_length(info.catchange_xip,1) >= 2 and info.committed_count >= 1 and array_length(info.committed_xip,1) >= 1; }
 
-permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_checkpoint" "s1_get_changes" "s0_commit" "s0_begin" "s0_insert" "s1_checkpoint" "s1_get_changes" "s0_commit" "s1_get_changes" "s1_get_logical_snapshot_info" "s1_get_logical_snapshot_meta"
+
+# Both s0 and s1 execute catalog-change transactions. When "s1_get_changes" is
+# executed, s0's transaction is still in progress, while s1's transaction has
+# already completed. Consequently, the logical decoding produces a snapshot at
+# the point where a RUNNING_XACTS record is generated by "s1_checkpoint".
+# This snapshot contains both two ongoing catalog-change transactions (from s0's
+# top-level and sub transactions) and one completed transaction (from s1).
+# "s1_check_snapshot_info" verifies whether the logical snapshot contains at
+# least the expected number of transactions, accounting for potential
+# additional catalog changes that may occur due to concurrent autoanalyze.
+permutation "s0_init" "s0_begin" "s0_savepoint" "s0_truncate" "s1_create_table" "s1_checkpoint" "s1_get_changes" "s1_check_snapshot_info" "s1_check_snapshot_meta" "s0_commit"
-- 
2.43.5