From 30e68a2abb3890c3292ff0b2422a7ea04d62acdd Mon Sep 17 00:00:00 2001 From: Noah Misch Date: Sat, 15 Aug 2020 10:15:53 -0700 Subject: Prevent concurrent SimpleLruTruncate() for any given SLRU. The SimpleLruTruncate() header comment states the new coding rule. To achieve this, add locktype "frozenid" and two LWLocks. This closes a rare opportunity for data loss, which manifested as "apparent wraparound" or "could not access status of transaction" errors. Data loss is more likely in pg_multixact, due to released branches' thin margin between multiStopLimit and multiWrapLimit. If a user's physical replication primary logged ": apparent wraparound" messages, the user should rebuild standbys of that primary regardless of symptoms. At less risk is a cluster having emitted "not accepting commands" errors or "must be vacuumed" warnings at some point. One can test a cluster for this data loss by running VACUUM FREEZE in every database. Back-patch to 9.5 (all supported versions). Discussion: https://postgr.es/m/20190218073103.GA1434723@rfd.leadboat.com --- src/backend/utils/adt/lockfuncs.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'src/backend/utils/adt/lockfuncs.c') diff --git a/src/backend/utils/adt/lockfuncs.c b/src/backend/utils/adt/lockfuncs.c index ffd1970f589..bb1add7dcfb 100644 --- a/src/backend/utils/adt/lockfuncs.c +++ b/src/backend/utils/adt/lockfuncs.c @@ -26,6 +26,7 @@ const char *const LockTagTypeNames[] = { "relation", "extend", + "frozenid", "page", "tuple", "transactionid", @@ -245,6 +246,17 @@ pg_lock_status(PG_FUNCTION_ARGS) nulls[8] = true; nulls[9] = true; break; + case LOCKTAG_DATABASE_FROZEN_IDS: + values[1] = ObjectIdGetDatum(instance->locktag.locktag_field1); + nulls[2] = true; + nulls[3] = true; + nulls[4] = true; + nulls[5] = true; + nulls[6] = true; + nulls[7] = true; + nulls[8] = true; + nulls[9] = true; + break; case LOCKTAG_PAGE: values[1] = ObjectIdGetDatum(instance->locktag.locktag_field1); values[2] = ObjectIdGetDatum(instance->locktag.locktag_field2); -- cgit v1.2.3