From 849222d30ec9cce21ca16ed42a3944074d234653 Mon Sep 17 00:00:00 2001 From: debebantur Date: Fri, 31 Jul 2026 08:11:23 +0000 Subject: [[PATCH] Fix timeline history after recovery stops on an ancestor] A recovery target can be reached before recovery switches to the requested timeline. Using recoveryTargetTLI as the parent in that case creates a history file that claims the new timeline forked from a timeline that recovery never reached.Use the timeline of the last replayed WAL record as the parent instead. Extend the existing PITR timeline test to verify the resulting history. --- src/backend/access/transam/xlog.c | 2 +- src/test/recovery/t/002_archiving.pl | 14 ++++++++++++++ src/test/recovery/t/028_pitr_timelines.pl | 9 +++++++++ 3 files changed, 24 insertions(+), 1 deletion(-) diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index f85b528608..6b0b27d853 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -6408,7 +6408,7 @@ StartupXLOG(void) * To minimize the window for that, try to do as little as possible * between here and writing the end-of-recovery record. */ - writeTimeLineHistory(newTLI, recoveryTargetTLI, + writeTimeLineHistory(newTLI, endOfRecoveryInfo->lastRecTLI, EndOfLog, endOfRecoveryInfo->recoveryStopReason); ereport(LOG, diff --git a/src/test/recovery/t/002_archiving.pl b/src/test/recovery/t/002_archiving.pl index aa40f58e6d..a7ff14b3a0 100644 --- a/src/test/recovery/t/002_archiving.pl +++ b/src/test/recovery/t/002_archiving.pl @@ -100,6 +100,20 @@ $caughtup_query = $node_primary->poll_query_until('postgres', $caughtup_query) or die "Timed out while waiting for archiving of 00000002.history"; +# Generate and archive some WAL on timeline 2. This ensures that standby2 +# actually reaches timeline 2, so that its history file is needed again when +# standby2 is promoted. +$node_standby->safe_psql('postgres', "CREATE TABLE timeline_2_marker (a int)"); +my $timeline_2_lsn = + $node_standby->safe_psql('postgres', "SELECT pg_current_wal_lsn()"); +my $timeline_2_walfile = $node_standby->safe_psql( + 'postgres', "SELECT pg_walfile_name('$timeline_2_lsn')"); +$node_standby->safe_psql('postgres', "SELECT pg_switch_wal()"); +$caughtup_query = + "SELECT size IS NOT NULL FROM pg_stat_file('$primary_archive/$timeline_2_walfile', true)"; +$node_primary->poll_query_until('postgres', $caughtup_query) + or die "Timed out while waiting for archiving of $timeline_2_walfile"; + # recovery_end_command should have been triggered on promotion. ok( -f "$data_dir/$recovery_end_command_file", 'recovery_end_command executed after promotion'); diff --git a/src/test/recovery/t/028_pitr_timelines.pl b/src/test/recovery/t/028_pitr_timelines.pl index ae617f6195..429b6e8220 100644 --- a/src/test/recovery/t/028_pitr_timelines.pl +++ b/src/test/recovery/t/028_pitr_timelines.pl @@ -150,6 +150,15 @@ $node_pitr->poll_query_until('postgres', # Stop the node. This archives the last segment. $node_pitr->stop(); +# The new timeline branched from timeline 1 at the recovery target, before +# timeline 2 branched from timeline 1. Its history must therefore name +# timeline 1 as its direct parent, rather than copying timeline 2's history. +my $history = slurp_file($node_primary->archive_dir . '/00000003.history'); +like( + $history, + qr/^1\t[0-9A-F]+\/[0-9A-F]+\t[^\r\n]*(?:\r?\n)?\z/, + "new timeline history has the timeline containing the target as parent"); + # Test archive recovery on the timeline created by the PITR. This # replays the end-of-recovery record that switches from timeline 1 to # 3. -- 2.34.1