TAP test to cover "EndOfLogTLI != replayTLI" case

From 88ae9ea5a33c1ecc5b5493dae9c016ef19fbf88f Mon Sep 17 00:00:00 2001
From: Amul Sul <amul.sul@enterprisedb.com>
Date: Sun, 9 Jan 2022 23:10:07 -0500
Subject: [PATCH v2] TAP test for EndOfLogTLI

---
 src/test/recovery/t/003_recovery_targets.pl | 52 ++++++++++++++++++++-
 1 file changed, 51 insertions(+), 1 deletion(-)

diff --git a/src/test/recovery/t/003_recovery_targets.pl b/src/test/recovery/t/003_recovery_targets.pl
index 24da78c0bcd..cf72b5d9343 100644
--- a/src/test/recovery/t/003_recovery_targets.pl
+++ b/src/test/recovery/t/003_recovery_targets.pl
@@ -6,7 +6,7 @@ use strict;
 use warnings;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
-use Test::More tests => 9;
+use Test::More tests => 10;
 use Time::HiRes qw(usleep);
 
 # Create and test a standby from given backup, with a certain recovery target.
@@ -182,3 +182,53 @@ $logfile = slurp_file($node_standby->logfile());
 ok( $logfile =~
 	  qr/FATAL: .* recovery ended before configured recovery target was reached/,
 	'recovery end before target reached is a fatal error');
+
+# Test to cover a case where that we are looking for WAL record that ought to be
+# in for e.g 000000010000000000000001 we don't find it; instead we find
+# 000000020000000000000003 because of various reasons such as there was a
+# timeline switch in that segment, and we were reading the old WAL from a
+# segment belonging to a higher timeline or our recovery target timeline is 2,
+# or something that has 2 in its history.
+
+# Insert few more data to primary
+$node_primary->safe_psql('postgres',
+	"INSERT INTO tab_int VALUES (generate_series(6001,7000))");
+my $lsn6 = $node_primary->safe_psql('postgres',
+	"SELECT pg_current_wal_lsn()");
+
+# Setup new standby and enable WAL archiving to archive WAL files at the same
+# location as the primary.
+my $archive_cmd = $node_primary->safe_psql('postgres',
+	"SELECT current_setting('archive_command')");
+$node_standby = PostgreSQL::Test::Cluster->new('standby_9');
+$node_standby->init_from_backup(
+	$node_primary, 'my_backup',
+	has_streaming => 1);
+$node_standby->append_conf(
+        'postgresql.conf', qq(
+archive_mode = on
+archive_command = '$archive_cmd'
+));
+$node_standby->start;
+# Wait until necessary replay has been done on standby
+$node_primary->wait_for_catchup($node_standby, 'replay',
+	$node_primary->lsn('write'));
+$node_standby->promote;
+$node_standby->safe_psql('postgres',
+	"INSERT INTO tab_int VALUES (generate_series(7001,8000))");
+# Force archiving of WAL file
+$node_standby->safe_psql('postgres', "SELECT pg_switch_wal()");
+$node_standby->stop;
+
+# Another standby whose recovery target lsn will be in the WAL file has
+# a different TLI than the target LSN belongs to.
+$node_standby = PostgreSQL::Test::Cluster->new('standby_10');
+$node_standby->init_from_backup(
+	$node_primary, 'my_backup',
+	has_restoring => 1);
+$node_standby->append_conf(
+        'postgresql.conf', qq(recovery_target_lsn = '$lsn6'));
+$node_standby->start;
+my $result = $node_standby->safe_psql('postgres',
+	"SELECT count(*) FROM tab_int");
+is($result, '7000', "check standby content before timeline switch $lsn6");
-- 
2.18.0

From 08d19c0ef2f464e8bf722ce13457acf3f9be47e8 Mon Sep 17 00:00:00 2001
From: Amul Sul <amul.sul@enterprisedb.com>
Date: Mon, 17 Jan 2022 06:25:30 -0500
Subject: [PATCH v3] TAP test for EndOfLogTLI

---
 src/test/recovery/t/003_recovery_targets.pl | 57 ++++++++++++++++++++-
 1 file changed, 56 insertions(+), 1 deletion(-)

diff --git a/src/test/recovery/t/003_recovery_targets.pl b/src/test/recovery/t/003_recovery_targets.pl
index 24da78c0bcd..928799b9490 100644
--- a/src/test/recovery/t/003_recovery_targets.pl
+++ b/src/test/recovery/t/003_recovery_targets.pl
@@ -6,7 +6,7 @@ use strict;
 use warnings;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
-use Test::More tests => 9;
+use Test::More tests => 10;
 use Time::HiRes qw(usleep);
 
 # Create and test a standby from given backup, with a certain recovery target.
@@ -182,3 +182,58 @@ $logfile = slurp_file($node_standby->logfile());
 ok( $logfile =~
 	  qr/FATAL: .* recovery ended before configured recovery target was reached/,
 	'recovery end before target reached is a fatal error');
+
+# Test to cover a case where that we are looking for WAL record that ought to be
+# in for e.g 000000010000000000000001 we don't find it; instead we find
+# 000000020000000000000003 because of various reasons such as there was a
+# timeline switch in that segment, and we were reading the old WAL from a
+# segment belonging to a higher timeline or our recovery target timeline is 2,
+# or something that has 2 in its history.
+
+# Insert few more data to primary
+$node_primary->safe_psql('postgres',
+	"INSERT INTO tab_int VALUES (generate_series(6001,7000))");
+my $lsn6 = $node_primary->safe_psql('postgres',
+	"SELECT pg_current_wal_lsn()");
+
+# Setup new standby and enable WAL archiving to archive WAL files at the same
+# location as the primary.
+my $archive_cmd = $node_primary->safe_psql('postgres',
+	"SELECT current_setting('archive_command')");
+$node_standby = PostgreSQL::Test::Cluster->new('standby_9');
+$node_standby->init_from_backup(
+	$node_primary, 'my_backup',
+	has_streaming => 1);
+$node_standby->append_conf(
+        'postgresql.conf', qq(
+archive_mode = on
+archive_command = '$archive_cmd'
+));
+$node_standby->start;
+# Wait until necessary replay has been done on standby
+$node_primary->wait_for_catchup($node_standby, 'replay',
+	$node_primary->lsn('write'));
+$node_standby->promote;
+$node_standby->safe_psql('postgres',
+	"INSERT INTO tab_int VALUES (generate_series(7001,8000))");
+# Force archiving of WAL file
+my $last_wal = $node_standby->safe_psql('postgres',
+	"SELECT pg_walfile_name(pg_switch_wal())");
+# Wait until this WAL file archive
+my $check_archive = "SELECT last_archived_wal >= '$last_wal' FROM pg_stat_archiver";
+$node_standby->poll_query_until('postgres', $check_archive)
+	or die "Timed out while waiting for $last_wal file archive";
+$node_standby->stop;
+
+# Another standby whose recovery target lsn will be in the WAL file has
+# a different TLI than the target LSN belongs to.
+$node_standby = PostgreSQL::Test::Cluster->new('standby_10');
+$node_standby->init_from_backup(
+	$node_primary, 'my_backup',
+	has_restoring => 1);
+$node_standby->append_conf(
+        'postgresql.conf', qq(recovery_target_lsn = '$lsn6'));
+$node_standby->start;
+my $result = $node_standby->safe_psql('postgres',
+	"SELECT count(*) FROM tab_int");
+is($result, '7000', "check standby content before timeline switch $lsn6");
-- 
2.18.0

From 4bc968d3508e9f608fd572f40f39e2cb374d53f4 Mon Sep 17 00:00:00 2001
From: Amul Sul <amul.sul@enterprisedb.com>
Date: Wed, 19 Jan 2022 23:22:02 -0500
Subject: [PATCH v4 1/3] Allow TAP tests to choose custom WAL archive and
 restore path.

---
 src/test/perl/PostgreSQL/Test/Cluster.pm | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/src/test/perl/PostgreSQL/Test/Cluster.pm b/src/test/perl/PostgreSQL/Test/Cluster.pm
index b7d4c24553..6a562db2ce 100644
--- a/src/test/perl/PostgreSQL/Test/Cluster.pm
+++ b/src/test/perl/PostgreSQL/Test/Cluster.pm
@@ -1033,10 +1033,13 @@ primary_conninfo='$root_connstr'
 # Internal routine to enable archive recovery command on a standby node
 sub enable_restoring
 {
-	my ($self, $root_node, $standby) = @_;
-	my $path = PostgreSQL::Test::Utils::perl2host($root_node->archive_dir);
+	my ($self, $root_node, $standby, $path) = @_;
 	my $name = $self->name;
 
+	# Default archive directory will be used if not specified.
+	$path = $root_node->archive_dir if (!defined($path));
+	$path = PostgreSQL::Test::Utils::perl2host($path);
+
 	print "### Enabling WAL restore for node \"$name\"\n";
 
 	# On Windows, the path specified in the restore command needs to use
@@ -1101,10 +1104,13 @@ sub set_standby_mode
 # Internal routine to enable archiving
 sub enable_archiving
 {
-	my ($self) = @_;
-	my $path   = PostgreSQL::Test::Utils::perl2host($self->archive_dir);
+	my ($self, $path) = @_;
 	my $name   = $self->name;
 
+	# Default archive directory will be used if not specified.
+	$path = $self->archive_dir if (!defined($path));
+	$path = PostgreSQL::Test::Utils::perl2host($path);
+
 	print "### Enabling WAL archiving for node \"$name\"\n";
 
 	# On Windows, the path specified in the restore command needs to use
-- 
2.18.0

From 6c730ee10b9e64d90982aa555283c9094a5fdb87 Mon Sep 17 00:00:00 2001
From: Amul Sul <amul.sul@enterprisedb.com>
Date: Wed, 19 Jan 2022 23:25:07 -0500
Subject: [PATCH v4 2/3] TAP test for EndOfLogTLI

---
 src/test/recovery/t/003_recovery_targets.pl | 47 ++++++++++++++++++++-
 1 file changed, 46 insertions(+), 1 deletion(-)

diff --git a/src/test/recovery/t/003_recovery_targets.pl b/src/test/recovery/t/003_recovery_targets.pl
index 24da78c0bc..b3f7076540 100644
--- a/src/test/recovery/t/003_recovery_targets.pl
+++ b/src/test/recovery/t/003_recovery_targets.pl
@@ -6,7 +6,7 @@ use strict;
 use warnings;
 use PostgreSQL::Test::Cluster;
 use PostgreSQL::Test::Utils;
-use Test::More tests => 9;
+use Test::More tests => 10;
 use Time::HiRes qw(usleep);
 
 # Create and test a standby from given backup, with a certain recovery target.
@@ -182,3 +182,48 @@ $logfile = slurp_file($node_standby->logfile());
 ok( $logfile =~
 	  qr/FATAL: .* recovery ended before configured recovery target was reached/,
 	'recovery end before target reached is a fatal error');
+
+# Test to cover a case where that we are looking for WAL record that ought to be
+# in for e.g 000000010000000000000005 we don't find it; instead we find
+# 000000020000000000000005 because of various reasons such as there was a
+# timeline switch in that segment, and we were reading the old WAL from a
+# segment belonging to a higher timeline or our recovery target timeline is 2,
+# or something that has 2 in its history.
+
+# Insert few more data to primary
+$node_primary->safe_psql('postgres', "SELECT pg_switch_wal()");
+$node_primary->safe_psql('postgres',
+	"INSERT INTO tab_int VALUES (generate_series(6001,7000))");
+my $lsn6 = $node_primary->safe_psql('postgres',
+	"SELECT pg_current_wal_lsn()");
+
+# Setup new standby and enable WAL archiving to archive WAL files at the same
+# location as the primary.
+my $archive_dir = $node_primary->archive_dir;
+$node_standby = PostgreSQL::Test::Cluster->new('standby_9');
+$node_standby->init_from_backup(
+	$node_primary, 'my_backup',
+	has_streaming => 1);
+$node_standby->enable_archiving($archive_dir);
+$node_standby->start;
+# Wait until necessary replay has been done on standby
+$node_primary->wait_for_catchup($node_standby);
+$node_standby->promote;
+$node_standby->safe_psql('postgres',
+	"INSERT INTO tab_int VALUES (generate_series(7001,8000))");
+# Force archiving of WAL file
+my $last_wal = $node_standby->safe_psql('postgres',
+	"SELECT pg_walfile_name(pg_switch_wal())");
+# Wait until this WAL file archive
+my $check_archive = "SELECT last_archived_wal >= '$last_wal' FROM pg_stat_archiver";
+$node_standby->poll_query_until('postgres', $check_archive)
+	or die "Timed out while waiting for $last_wal file archive";
+$node_standby->stop;
+
+# Another standby whose recovery target lsn will be in the WAL file has
+# a different TLI than the target LSN belongs to.
+@recovery_params = (
+	"recovery_target_lsn = '$lsn6'",
+	"recovery_target_inclusive = off");
+test_recovery_standby("target LSN belong to different TLI",
+	'standby_10', $node_primary, \@recovery_params, "7000", $lsn6);
-- 
2.18.0