postgres.git / summary / log / commit / refs

commit    caaeb88ff7ae84a3bbf0ee497a4bda18cf9261cd
Author:   Alvaro Herrera <alvherre@alvh.no-ip.org>
Date:     Wed Mar 23 17:22:10 2022 +0000

    Fix "missing continuation record" after standby promotion
    
    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


 src/backend/access/transam/xlog.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/xlog.c b/src/backend/access/transam/xlog.c
index 3e71aea71f3..b89c58118e9 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -10592,6 +10592,10 @@ VerifyOverwriteContrecord(xl_overwrite_contrecord *xlrec, XLogReaderState *state
 			 LSN_FORMAT_ARGS(xlrec->overwritten_lsn),
 			 LSN_FORMAT_ARGS(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",
 					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 cb7f5b68c65..d451fe6b224 100644
--- a/src/test/recovery/t/026_overwrite_contrecord.pl
+++ b/src/test/recovery/t/026_overwrite_contrecord.pl
@@ -15,7 +15,7 @@ plan tests => 3;
 # 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 @@ like(
 	qr[successfully skipped missing contrecord at],
 	"found log line in standby");
 
+# Verify promotion is successful
+$node_standby->promote;
+
 $node->stop;
 $node_standby->stop;


[parent: cd3a5055f952]