From 0b208cb5f1cdd5226e6e7db6784baf12d20af1fb Mon Sep 17 00:00:00 2001 From: Manu Date: Thu, 22 Oct 2026 11:15:44 -0300 Subject: [PATCH v2] Fix assertion failure in WAL summarizer after promotion A standby's WAL summarizer summarizes up to what the walreceiver has flushed, which can be well past the point where replay stops at a recovery target. If the standby is then promoted, the old timeline ends at a switch point that the summarizer has already passed. When the summarizer notices the new timeline while waiting for WAL inside SummarizeWAL(), summarizer_read_local_xlog_page() moves read_upto backwards to the switch point, as its comments anticipate, and the next read hits end of WAL. SummarizeWAL() then reported read_upto as the end of the summary, an LSN before the one it started from, and WalSummarizerMain() failed Assert(end_of_summary_lsn >= current_lsn) Builds without assertions were not affected in practice: the main loop treated the bogus end LSN as its new position, noticed the timeline switch on its next iteration and resumed from the switch point on the new timeline. Fix by having SummarizeWAL() report no progress in that case. The main loop then backs up to the switch point through the code that already exists for that purpose. Add a test reproducing the scenario reported by Fujii Masao. Reported-by: Fujii Masao Reviewed-by: Daria Lepikhova Tested-by: Daria Lepikhova Discussion: https://postgr.es/m/CAHGQGwFbpzR2Wkrku9J8w6E+-rzD6Ovazs8n_kxvzfccfnJ0tg@mail.gmail.com Backpatch-through: 17 --- src/backend/postmaster/walsummarizer.c | 16 +++- src/bin/pg_walsummary/meson.build | 1 + .../t/004_promote_past_target.pl | 77 +++++++++++++++++++ 3 files changed, 93 insertions(+), 1 deletion(-) create mode 100644 src/bin/pg_walsummary/t/004_promote_past_target.pl diff --git a/src/backend/postmaster/walsummarizer.c b/src/backend/postmaster/walsummarizer.c index 8333a4e..88b6fee 100644 --- a/src/backend/postmaster/walsummarizer.c +++ b/src/backend/postmaster/walsummarizer.c @@ -1287,6 +1287,18 @@ SummarizeWAL(TimeLineID tli, XLogRecPtr start_lsn, bool exact, break; } + /* + * If the timeline we were reading became historic while we were waiting + * for more WAL, summarizer_read_local_xlog_page() may have moved read_upto + * backwards to a switch point that precedes the point where this summary + * started (for example, when a standby that has summarized WAL beyond its + * recovery target is promoted). In that case we have summarized nothing, + * so report that we made no progress. The caller will notice the timeline + * switch on its next iteration and back up to the switch point. + */ + if (summary_end_lsn < summary_start_lsn) + summary_end_lsn = summary_start_lsn; + /* Destroy xlogreader. */ pfree(xlogreader->private_data); XLogReaderFree(xlogreader); @@ -1729,7 +1741,9 @@ summarizer_read_local_xlog_page(XLogReaderState *state, * backwards, because we might have been promoted before * reaching the end of the previous timeline. In that * case, the next loop iteration will likely conclude that - * we've reached end of WAL. + * we've reached end of WAL. If the switch point precedes + * the start of the current summary, SummarizeWAL() then + * reports no progress. */ private_data->read_upto = switchpoint; diff --git a/src/bin/pg_walsummary/meson.build b/src/bin/pg_walsummary/meson.build index 839b644..46e0207 100644 --- a/src/bin/pg_walsummary/meson.build +++ b/src/bin/pg_walsummary/meson.build @@ -26,6 +26,7 @@ tests += { 't/001_basic.pl', 't/002_blocks.pl', 't/003_tli_switch.pl', + 't/004_promote_past_target.pl', ], } } diff --git a/src/bin/pg_walsummary/t/004_promote_past_target.pl b/src/bin/pg_walsummary/t/004_promote_past_target.pl new file mode 100644 index 0000000..7672183 --- /dev/null +++ b/src/bin/pg_walsummary/t/004_promote_past_target.pl @@ -0,0 +1,77 @@ +# Copyright (c) 2021-2026, PostgreSQL Global Development Group +# +# A standby that stops at a recovery target can have summarized WAL beyond +# that target, because the WAL summarizer reads whatever the walreceiver has +# flushed. When such a standby is promoted, the old timeline ends at a point +# the summarizer has already passed. The summarizer must back up to the switch +# point and continue on the new timeline, rather than report a summary that +# ends before it started (which used to trip an assertion). + +use strict; +use warnings FATAL => 'all'; +use PostgreSQL::Test::Cluster; +use PostgreSQL::Test::Utils; +use Test::More; + +my $primary = PostgreSQL::Test::Cluster->new('primary'); +$primary->init(allows_streaming => 1); +$primary->append_conf('postgresql.conf', <start; + +$primary->safe_psql('postgres', 'CREATE TABLE t (i int)'); +$primary->backup('backup'); + +# The recovery target is the redo pointer of a checkpoint, so that the +# standby's summarizer completes a summary that starts exactly there before +# promotion; a second checkpoint lets it summarize past the target. +$primary->safe_psql('postgres', 'INSERT INTO t VALUES (1); CHECKPOINT;'); +my $target_lsn = $primary->safe_psql('postgres', + 'SELECT redo_lsn FROM pg_control_checkpoint()'); +$primary->safe_psql('postgres', 'INSERT INTO t VALUES (2); CHECKPOINT;'); + +my $standby = PostgreSQL::Test::Cluster->new('standby'); +$standby->init_from_backup($primary, 'backup', has_streaming => 1); +$standby->append_conf('postgresql.conf', <start; + +# Wait until replay is paused at the target, the summarizer has summarized +# past it on timeline 1, and the summarizer is waiting for more WAL. +$standby->poll_query_until('postgres', + "SELECT pg_get_wal_replay_pause_state() = 'paused'") + or die "timed out waiting for recovery to pause"; +$standby->poll_query_until('postgres', <poll_query_until('postgres', <logfile; +$standby->promote; +$standby->safe_psql('postgres', 'CHECKPOINT'); + +# Summarization must resume on timeline 2 exactly at the switch point. +my $result = $standby->poll_query_until('postgres', <log_contains( + qr/WAL summarizer process .* was terminated by signal/, $log_offset), + 'no WAL summarizer crash after promotion'); + +done_testing(); -- 2.56.0