Test restartpoints in archive recovery.

nmisch · nmisch · commit 4399d1055627 · 2025-04-20T08:28:53.000-07:00
v14 commit 1f95181 and its v13 equivalent caused timing-dependent failures in archive recovery, at restartpoints. The symptom was "invalid magic number 0000 in log segment X, offset 0", "unexpected pageaddr X in log segment Y, offset 0" [X < Y], or an assertion failure. Commit 3635a0a and predecessors back-patched v15 changes to fix that. This test reproduces the problem probabilistically, typically in less than 1000 iterations of the test. Hence, buildfarm and CI runs would have surfaced enough failures to get attention within a day. Reported-by: Arun Thirupathi <arunth@google.com> Discussion: https://postgr.es/m/20250306193013.36.nmisch@google.com Backpatch-through: 13
diff --git a/src/test/recovery/t/045_archive_restartpoint.pl b/src/test/recovery/t/045_archive_restartpoint.pl
@@ -0,0 +1,57 @@
+
+# Copyright (c) 2024-2025, PostgreSQL Global Development Group
+
+# Test restartpoints during archive recovery.
+use strict;
+use warnings;
+
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+my $archive_max_mb = 320;
+my $wal_segsize = 1;
+
+# Initialize primary node
+my $node_primary = PostgreSQL::Test::Cluster->new('primary');
+$node_primary->init(
+	has_archiving => 1,
+	allows_streaming => 1,
+	extra => [ '--wal-segsize' => $wal_segsize ]);
+$node_primary->start;
+my $backup_name = 'my_backup';
+$node_primary->backup($backup_name);
+
+$node_primary->safe_psql('postgres',
+	('DO $$BEGIN FOR i IN 1..' . $archive_max_mb / $wal_segsize)
+	  . ' LOOP CHECKPOINT; PERFORM pg_switch_wal(); END LOOP; END$$;');
+
+# Force archiving of WAL file containing recovery target
+my $until_lsn = $node_primary->lsn('write');
+$node_primary->safe_psql('postgres', "SELECT pg_switch_wal()");
+$node_primary->stop;
+
+# Archive recovery
+my $node_restore = PostgreSQL::Test::Cluster->new('restore');
+$node_restore->init_from_backup($node_primary, $backup_name,
+	has_restoring => 1);
+$node_restore->append_conf('postgresql.conf',
+	"recovery_target_lsn = '$until_lsn'");
+$node_restore->append_conf('postgresql.conf',
+	'recovery_target_action = pause');
+$node_restore->append_conf('postgresql.conf',
+	'max_wal_size = ' . 2 * $wal_segsize);
+$node_restore->append_conf('postgresql.conf', 'log_checkpoints = on');
+
+$node_restore->start;
+
+# Wait until restore has replayed enough data
+my $caughtup_query =
+  "SELECT '$until_lsn'::pg_lsn <= pg_last_wal_replay_lsn()";
+$node_restore->poll_query_until('postgres', $caughtup_query)
+  or die "Timed out while waiting for restore to catch up";
+
+$node_restore->stop;
+ok(1, 'restore caught up');
+
+done_testing();
