1
0
mirror of https://github.com/postgres/postgres.git synced 2025-06-29 10:41:53 +03:00

During recovery, if we reach consistent state and still have entries in the

invalid-page hash table, PANIC immediately. Immediate PANIC is much better
than waiting for end-of-recovery, which is what we did before, because the
end-of-recovery might not come until months later if this is a standby
server.

Also refrain from creating a restartpoint if there are invalid-page entries
in the hash table. Restarting recovery from such a restartpoint would not
see the invalid references, and wouldn't be able to cross-check them when
consistency is reached. That wouldn't matter when things are going smoothly,
but the more sanity checks you have the better.

Fujii Masao
This commit is contained in:
Heikki Linnakangas
2011-12-02 10:49:54 +02:00
parent 15a5006aac
commit 1e616f6391
4 changed files with 70 additions and 28 deletions

View File

@ -562,7 +562,7 @@ static TimeLineID lastPageTLI = 0;
static XLogRecPtr minRecoveryPoint; /* local copy of
* ControlFile->minRecoveryPoint */
static bool updateMinRecoveryPoint = true;
static bool reachedMinRecoveryPoint = false;
bool reachedMinRecoveryPoint = false;
static bool InRedo = false;
@ -6758,12 +6758,6 @@ StartupXLOG(void)
/* Disallow XLogInsert again */
LocalXLogInsertAllowed = -1;
/*
* Check to see if the XLOG sequence contained any unresolved
* references to uninitialized pages.
*/
XLogCheckInvalidPages();
/*
* Perform a checkpoint to update all our recovery activity to disk.
*
@ -6906,6 +6900,12 @@ CheckRecoveryConsistency(void)
XLByteLE(minRecoveryPoint, EndRecPtr) &&
XLogRecPtrIsInvalid(ControlFile->backupStartPoint))
{
/*
* Check to see if the XLOG sequence contained any unresolved
* references to uninitialized pages.
*/
XLogCheckInvalidPages();
reachedMinRecoveryPoint = true;
ereport(LOG,
(errmsg("consistent recovery state reached at %X/%X",
@ -7907,7 +7907,7 @@ RecoveryRestartPoint(const CheckPoint *checkPoint)
volatile XLogCtlData *xlogctl = XLogCtl;
/*
* Is it safe to checkpoint? We must ask each of the resource managers
* Is it safe to restartpoint? We must ask each of the resource managers
* whether they have any partial state information that might prevent a
* correct restart from this point. If so, we skip this opportunity, but
* return at the next checkpoint record for another try.
@ -7926,6 +7926,22 @@ RecoveryRestartPoint(const CheckPoint *checkPoint)
}
}
/*
* Also refrain from creating a restartpoint if we have seen any references
* to non-existent pages. Restarting recovery from the restartpoint would
* not see the references, so we would lose the cross-check that the pages
* belonged to a relation that was dropped later.
*/
if (XLogHaveInvalidPages())
{
elog(trace_recovery(DEBUG2),
"could not record restart point at %X/%X because there "
"are unresolved references to invalid pages",
checkPoint->redo.xlogid,
checkPoint->redo.xrecoff);
return;
}
/*
* Copy the checkpoint record to shared memory, so that checkpointer
* can work out the next time it wants to perform a restartpoint.