summaryrefslogtreecommitdiff
path: root/src/backend/commands/vacuum.c
diff options
context:
space:
mode:
authorNoah Misch <noah@leadboat.com>2020-08-15 10:15:53 -0700
committerNoah Misch <noah@leadboat.com>2020-08-15 10:15:57 -0700
commit3fbbf64ceecbd0fe675850070ea1e5d77c401c4f (patch)
tree9e7021dbabf53488b004337a94ca2c4a66fed09d /src/backend/commands/vacuum.c
parent5190707d7436089a33dd0e83482a314333ab6e59 (diff)
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
Diffstat (limited to 'src/backend/commands/vacuum.c')
-rw-r--r--src/backend/commands/vacuum.c13
1 files changed, 13 insertions, 0 deletions
diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c
index ebc76eaa207..43199cd5ffa 100644
--- a/src/backend/commands/vacuum.c
+++ b/src/backend/commands/vacuum.c
@@ -884,6 +884,14 @@ vac_update_datfrozenxid(void)
bool dirty = false;
/*
+ * Restrict this task to one backend per database. This avoids race
+ * conditions that would move datfrozenxid or datminmxid backward. It
+ * avoids calling vac_truncate_clog() with a datfrozenxid preceding a
+ * datfrozenxid passed to an earlier vac_truncate_clog() call.
+ */
+ LockDatabaseFrozenIds(ExclusiveLock);
+
+ /*
* Initialize the "min" calculation with GetOldestXmin, which is a
* reasonable approximation to the minimum relfrozenxid for not-yet-
* committed pg_class entries for new tables; see AddNewRelationTuple().
@@ -1047,6 +1055,9 @@ vac_truncate_clog(TransactionId frozenXID,
bool bogus = false;
bool frozenAlreadyWrapped = false;
+ /* Restrict task to one backend per cluster; see SimpleLruTruncate(). */
+ LWLockAcquire(WrapLimitsVacuumLock, LW_EXCLUSIVE);
+
/* init oldest datoids to sync with my frozenXID/minMulti values */
oldestxid_datoid = MyDatabaseId;
minmulti_datoid = MyDatabaseId;
@@ -1148,6 +1159,8 @@ vac_truncate_clog(TransactionId frozenXID,
SetTransactionIdLimit(frozenXID, oldestxid_datoid);
SetMultiXactIdLimit(minMulti, minmulti_datoid);
AdvanceOldestCommitTsXid(frozenXID);
+
+ LWLockRelease(WrapLimitsVacuumLock);
}