diff options
| author | Alexander Korotkov <akorotkov@postgresql.org> | 2024-08-10 21:43:02 +0300 |
|---|---|---|
| committer | Alexander Korotkov <akorotkov@postgresql.org> | 2024-08-10 21:43:02 +0300 |
| commit | 867d396ccd2a7f0ce55e1fa7ebda00bc8c81147b (patch) | |
| tree | 2af07b058abba4f384d06781a952203e1c250842 /src/backend/commands/waitlsn.c | |
| parent | bbf668d66fbf61d45f1c187b08a5f51537bfb7c7 (diff) | |
| download | postgresql-867d396ccd2a7f0ce55e1fa7ebda00bc8c81147b.tar.gz postgresql-867d396ccd2a7f0ce55e1fa7ebda00bc8c81147b.zip | |
Adjust pg_wal_replay_wait() procedure behavior on promoted standby
pg_wal_replay_wait() is intended to be called on standby. However, standby
can be promoted to primary at any moment, even concurrently with the
pg_wal_replay_wait() call. If recovery is not currently in progress
that doesn't mean the wait was unsuccessful. Thus, we always need to recheck
if the target LSN is replayed.
Reported-by: Kevin Hale Boyes
Discussion: https://postgr.es/m/CAPpHfdu5QN%2BZGACS%2B7foxmr8_nekgA2PA%2B-G3BuOUrdBLBFb6Q%40mail.gmail.com
Author: Alexander Korotkov
Diffstat (limited to 'src/backend/commands/waitlsn.c')
| -rw-r--r-- | src/backend/commands/waitlsn.c | 42 |
1 files changed, 33 insertions, 9 deletions
diff --git a/src/backend/commands/waitlsn.c b/src/backend/commands/waitlsn.c index 3170f0792a5..deefbd458c0 100644 --- a/src/backend/commands/waitlsn.c +++ b/src/backend/commands/waitlsn.c @@ -230,14 +230,27 @@ WaitForLSNReplay(XLogRecPtr targetLSN, int64 timeout) Assert(MyProcNumber >= 0 && MyProcNumber < MaxBackends); if (!RecoveryInProgress()) + { + /* + * Recovery is not in progress. Given that we detected this in the + * very first check, this procedure was mistakenly called on primary. + * However, it's possible that standby was promoted concurrently to + * the procedure call, while target LSN is replayed. So, we still + * check the last replay LSN before reporting an error. + */ + if (targetLSN <= GetXLogReplayRecPtr(NULL)) + return; ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("recovery is not in progress"), errhint("Waiting for LSN can only be executed during recovery."))); - - /* If target LSN is already replayed, exit immediately */ - if (targetLSN <= GetXLogReplayRecPtr(NULL)) - return; + } + else + { + /* If target LSN is already replayed, exit immediately */ + if (targetLSN <= GetXLogReplayRecPtr(NULL)) + return; + } if (timeout > 0) { @@ -257,19 +270,30 @@ WaitForLSNReplay(XLogRecPtr targetLSN, int64 timeout) int rc; long delay_ms = 0; - /* Check if the waited LSN has been replayed */ - currentLSN = GetXLogReplayRecPtr(NULL); - if (targetLSN <= currentLSN) - break; - /* Recheck that recovery is still in-progress */ if (!RecoveryInProgress()) + { + /* + * Recovery was ended, but recheck if target LSN was already + * replayed. + */ + currentLSN = GetXLogReplayRecPtr(NULL); + if (targetLSN <= currentLSN) + return; ereport(ERROR, (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("recovery is not in progress"), errdetail("Recovery ended before replaying target LSN %X/%X; last replay LSN %X/%X.", LSN_FORMAT_ARGS(targetLSN), LSN_FORMAT_ARGS(currentLSN)))); + } + else + { + /* Check if the waited LSN has been replayed */ + currentLSN = GetXLogReplayRecPtr(NULL); + if (targetLSN <= currentLSN) + break; + } /* * If the timeout value is specified, calculate the number of |