Fix "missing continuation record" after standby promotion

alvherre · alvherre · commit 98eb3e06ce3a · 2022-03-23T18:22:10.000+01:00
Invalidate abortedRecPtr and missingContrecPtr after a missing continuation record is successfully 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. Backpatch to 10 (all stable versions). Author: Sami Imseih <simseih@amazon.com> Reviewed-by: Kyotaro Horiguchi <horikyota.ntt@gmail.com> Reviewed-by: Álvaro Herrera <alvherre@alvh.no-ip.org> Discussion: https://postgr.es/m/44D259DE-7542-49C4-8A52-2AB01534DCA9@amazon.com
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
@@ -10383,6 +10383,10 @@ VerifyOverwriteContrecord(xl_overwrite_contrecord *xlrec, XLogReaderState *state
 			 (uint32) (state->overwrittenRecPtr >> 32),
 			 (uint32) state->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",
 					(uint32) (xlrec->overwritten_lsn >> 32),
diff --git a/src/test/recovery/t/026_overwrite_contrecord.pl b/src/test/recovery/t/026_overwrite_contrecord.pl
@@ -15,7 +15,7 @@
 # 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 = PostgresNode->get_new_node('primary');
 $node->init(allows_streaming => 1);
@@ -102,5 +102,8 @@ END
 	qr[successfully skipped missing contrecord at],
 	"found log line in standby");
 
+# Verify promotion is successful
+$node_standby->promote;
+
 $node->stop;
 $node_standby->stop;
