database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-03 09:13:20 +03:00
Code Activity

Adjust pg_wal_replay_wait() procedure behavior on promoted standby

Browse Source 
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
This commit is contained in:
Alexander Korotkov
2024-08-10 21:43:02 +03:00
parent bbf668d66f
commit 867d396ccd
3 changed files with 55 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
src/backend/commands/waitlsn.c
View File

@@ -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