mirror of
https://github.com/postgres/postgres.git
synced 2025-11-09 06:21:09 +03:00
Fix possible recovery trouble if TRUNCATE overlaps a checkpoint.
If TRUNCATE causes some buffers to be invalidated and thus the checkpoint does not flush them, TRUNCATE must also ensure that the corresponding files are truncated on disk. Otherwise, a replay from the checkpoint might find that the buffers exist but have the wrong contents, which may cause replay to fail. Report by Teja Mupparti. Patch by Kyotaro Horiguchi, per a design suggestion from Heikki Linnakangas, with some changes to the comments by me. Review of this and a prior patch that approached the issue differently by Heikki Linnakangas, Andres Freund, Álvaro Herrera, Masahiko Sawada, and Tom Lane. Discussion: http://postgr.es/m/BYAPR06MB6373BF50B469CA393C614257ABF00@BYAPR06MB6373.namprd06.prod.outlook.com
This commit is contained in:
@@ -3088,8 +3088,8 @@ TruncateMultiXact(MultiXactId newOldestMulti, Oid newOldestMultiDB)
|
||||
* crash/basebackup, even though the state of the data directory would
|
||||
* require it.
|
||||
*/
|
||||
Assert(!MyProc->delayChkpt);
|
||||
MyProc->delayChkpt = true;
|
||||
Assert((MyProc->delayChkpt & DELAY_CHKPT_START) == 0);
|
||||
MyProc->delayChkpt |= DELAY_CHKPT_START;
|
||||
|
||||
/* WAL log truncation */
|
||||
WriteMTruncateXlogRec(newOldestMultiDB,
|
||||
@@ -3115,7 +3115,7 @@ TruncateMultiXact(MultiXactId newOldestMulti, Oid newOldestMultiDB)
|
||||
/* Then offsets */
|
||||
PerformOffsetsTruncation(oldestMulti, newOldestMulti);
|
||||
|
||||
MyProc->delayChkpt = false;
|
||||
MyProc->delayChkpt &= ~DELAY_CHKPT_START;
|
||||
|
||||
END_CRIT_SECTION();
|
||||
LWLockRelease(MultiXactTruncationLock);
|
||||
|
||||
@@ -475,7 +475,7 @@ MarkAsPreparingGuts(GlobalTransaction gxact, TransactionId xid, const char *gid,
|
||||
}
|
||||
proc->xid = xid;
|
||||
Assert(proc->xmin == InvalidTransactionId);
|
||||
proc->delayChkpt = false;
|
||||
proc->delayChkpt = 0;
|
||||
proc->statusFlags = 0;
|
||||
proc->pid = 0;
|
||||
proc->databaseId = databaseid;
|
||||
@@ -1164,7 +1164,8 @@ EndPrepare(GlobalTransaction gxact)
|
||||
|
||||
START_CRIT_SECTION();
|
||||
|
||||
MyProc->delayChkpt = true;
|
||||
Assert((MyProc->delayChkpt & DELAY_CHKPT_START) == 0);
|
||||
MyProc->delayChkpt |= DELAY_CHKPT_START;
|
||||
|
||||
XLogBeginInsert();
|
||||
for (record = records.head; record != NULL; record = record->next)
|
||||
@@ -1207,7 +1208,7 @@ EndPrepare(GlobalTransaction gxact)
|
||||
* checkpoint starting after this will certainly see the gxact as a
|
||||
* candidate for fsyncing.
|
||||
*/
|
||||
MyProc->delayChkpt = false;
|
||||
MyProc->delayChkpt &= ~DELAY_CHKPT_START;
|
||||
|
||||
/*
|
||||
* Remember that we have this GlobalTransaction entry locked for us. If
|
||||
@@ -2266,7 +2267,8 @@ RecordTransactionCommitPrepared(TransactionId xid,
|
||||
START_CRIT_SECTION();
|
||||
|
||||
/* See notes in RecordTransactionCommit */
|
||||
MyProc->delayChkpt = true;
|
||||
Assert((MyProc->delayChkpt & DELAY_CHKPT_START) == 0);
|
||||
MyProc->delayChkpt |= DELAY_CHKPT_START;
|
||||
|
||||
/*
|
||||
* Emit the XLOG commit record. Note that we mark 2PC commits as
|
||||
@@ -2314,7 +2316,7 @@ RecordTransactionCommitPrepared(TransactionId xid,
|
||||
TransactionIdCommitTree(xid, nchildren, children);
|
||||
|
||||
/* Checkpoint can proceed now */
|
||||
MyProc->delayChkpt = false;
|
||||
MyProc->delayChkpt &= ~DELAY_CHKPT_START;
|
||||
|
||||
END_CRIT_SECTION();
|
||||
|
||||
|
||||
@@ -1387,8 +1387,9 @@ RecordTransactionCommit(void)
|
||||
* This makes checkpoint's determination of which xacts are delayChkpt
|
||||
* a bit fuzzy, but it doesn't matter.
|
||||
*/
|
||||
Assert((MyProc->delayChkpt & DELAY_CHKPT_START) == 0);
|
||||
START_CRIT_SECTION();
|
||||
MyProc->delayChkpt = true;
|
||||
MyProc->delayChkpt |= DELAY_CHKPT_START;
|
||||
|
||||
SetCurrentTransactionStopTimestamp();
|
||||
|
||||
@@ -1489,7 +1490,7 @@ RecordTransactionCommit(void)
|
||||
*/
|
||||
if (markXidCommitted)
|
||||
{
|
||||
MyProc->delayChkpt = false;
|
||||
MyProc->delayChkpt &= ~DELAY_CHKPT_START;
|
||||
END_CRIT_SECTION();
|
||||
}
|
||||
|
||||
|
||||
@@ -6517,18 +6517,30 @@ CreateCheckPoint(int flags)
|
||||
* and we will correctly flush the update below. So we cannot miss any
|
||||
* xacts we need to wait for.
|
||||
*/
|
||||
vxids = GetVirtualXIDsDelayingChkpt(&nvxids);
|
||||
vxids = GetVirtualXIDsDelayingChkpt(&nvxids, DELAY_CHKPT_START);
|
||||
if (nvxids > 0)
|
||||
{
|
||||
do
|
||||
{
|
||||
pg_usleep(10000L); /* wait for 10 msec */
|
||||
} while (HaveVirtualXIDsDelayingChkpt(vxids, nvxids));
|
||||
} while (HaveVirtualXIDsDelayingChkpt(vxids, nvxids,
|
||||
DELAY_CHKPT_START));
|
||||
}
|
||||
pfree(vxids);
|
||||
|
||||
CheckPointGuts(checkPoint.redo, flags);
|
||||
|
||||
vxids = GetVirtualXIDsDelayingChkpt(&nvxids, DELAY_CHKPT_COMPLETE);
|
||||
if (nvxids > 0)
|
||||
{
|
||||
do
|
||||
{
|
||||
pg_usleep(10000L); /* wait for 10 msec */
|
||||
} while (HaveVirtualXIDsDelayingChkpt(vxids, nvxids,
|
||||
DELAY_CHKPT_COMPLETE));
|
||||
}
|
||||
pfree(vxids);
|
||||
|
||||
/*
|
||||
* Take a snapshot of running transactions and write this to WAL. This
|
||||
* allows us to reconstruct the state of running transactions during
|
||||
|
||||
@@ -1011,7 +1011,7 @@ XLogSaveBufferForHint(Buffer buffer, bool buffer_std)
|
||||
/*
|
||||
* Ensure no checkpoint can change our view of RedoRecPtr.
|
||||
*/
|
||||
Assert(MyProc->delayChkpt);
|
||||
Assert((MyProc->delayChkpt & DELAY_CHKPT_START) != 0);
|
||||
|
||||
/*
|
||||
* Update RedoRecPtr so that we can make the right decision
|
||||
|
||||
Reference in New Issue
Block a user