From a43c4dc01c27a07798c935cbc15260d1a668d3b9 Mon Sep 17 00:00:00 2001 From: "Sami Imseih (AWS)" Date: Fri, 25 Feb 2022 21:23:34 +0000 Subject: [PATCH 1/1] Fix "missing continuation record" after standby promotion Invalidate abortedRecPtr and missingContrecPtr after a missing continuation record is skipped on a standby. This fixes a PANIC caused when a recently promoted standby attempts to write an OVERWRITE_RECORD with an LSN of the previously read aborted record. Author: Sami Imseih Reviewed-by: Kyotaro Horiguchi , Alvaro Herrera Discussion: https://postgr.es/m/44D259DE-7542-49C4-8A52-2AB01534DCA9@amazon.co --- src/backend/access/transam/xlogrecovery.c | 4 ++++ src/test/recovery/t/026_overwrite_contrecord.pl | 5 ++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c index f9f212680b..bbb2d7fef5 100644 --- a/src/backend/access/transam/xlogrecovery.c +++ b/src/backend/access/transam/xlogrecovery.c @@ -1948,6 +1948,10 @@ xlogrecovery_redo(XLogReaderState *record, TimeLineID replayTLI) LSN_FORMAT_ARGS(xlrec.overwritten_lsn), LSN_FORMAT_ARGS(record->overwrittenRecPtr)); + /* We have safely skipped the aborted record */ + abortedRecPtr = InvalidXLogRecPtr; + missingContrecPtr = InvalidXLogRecPtr; + ereport(LOG, (errmsg("successfully skipped missing contrecord at %X/%X, overwritten at %s", LSN_FORMAT_ARGS(xlrec.overwritten_lsn), diff --git a/src/test/recovery/t/026_overwrite_contrecord.pl b/src/test/recovery/t/026_overwrite_contrecord.pl index 0fd907f152..fe175f5e90 100644 --- a/src/test/recovery/t/026_overwrite_contrecord.pl +++ b/src/test/recovery/t/026_overwrite_contrecord.pl @@ -13,7 +13,7 @@ use Test::More; # Test: Create a physical replica that's missing the last WAL file, # then restart the primary to create a divergent WAL file and observe # that the replica replays the "overwrite contrecord" from that new -# file. +# file and the standby promotes successfully. my $node = PostgreSQL::Test::Cluster->new('primary'); $node->init(allows_streaming => 1); @@ -100,6 +100,9 @@ like( qr[successfully skipped missing contrecord at], "found log line in standby"); +# Verify promotion is successful +$node_standby->safe_psql('postgres', "select pg_promote()"); + $node->stop; $node_standby->stop; -- 2.32.0