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

1 files changed, 19 insertions, 7 deletions

diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index f047f9a242c..ae71d7538be 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -689,7 +689,10 @@ ProcArrayEndTransaction(PGPROC *proc, TransactionId latestXid)
 
 		proc->lxid = InvalidLocalTransactionId;
 		proc->xmin = InvalidTransactionId;
-		proc->delayChkpt = false;	/* be sure this is cleared in abort */
+
+		/* be sure this is cleared in abort */
+		proc->delayChkpt = 0;
+
 		proc->recoveryConflictPending = false;
 
 		/* must be cleared with xid/xmin: */
@@ -728,7 +731,10 @@ ProcArrayEndTransactionInternal(PGPROC *proc, TransactionId latestXid)
 	proc->xid = InvalidTransactionId;
 	proc->lxid = InvalidLocalTransactionId;
 	proc->xmin = InvalidTransactionId;
-	proc->delayChkpt = false;	/* be sure this is cleared in abort */
+
+	/* be sure this is cleared in abort */
+	proc->delayChkpt = 0;
+
 	proc->recoveryConflictPending = false;
 
 	/* must be cleared with xid/xmin: */
@@ -3043,7 +3049,8 @@ GetOldestSafeDecodingTransactionId(bool catalogOnly)
  * delaying checkpoint because they have critical actions in progress.
  *
  * Constructs an array of VXIDs of transactions that are currently in commit
- * critical sections, as shown by having delayChkpt set in their PGPROC.
+ * critical sections, as shown by having specified delayChkpt bits set in their
+ * PGPROC.
  *
  * Returns a palloc'd array that should be freed by the caller.
  * *nvxids is the number of valid entries.
@@ -3057,13 +3064,15 @@ GetOldestSafeDecodingTransactionId(bool catalogOnly)
  * for clearing of delayChkpt to propagate is unimportant for correctness.
  */
 VirtualTransactionId *
-GetVirtualXIDsDelayingChkpt(int *nvxids)
+GetVirtualXIDsDelayingChkpt(int *nvxids, int type)
 {
 	VirtualTransactionId *vxids;
 	ProcArrayStruct *arrayP = procArray;
 	int			count = 0;
 	int			index;
 
+	Assert(type != 0);
+
 	/* allocate what's certainly enough result space */
 	vxids = (VirtualTransactionId *)
 		palloc(sizeof(VirtualTransactionId) * arrayP->maxProcs);
@@ -3075,7 +3084,7 @@ GetVirtualXIDsDelayingChkpt(int *nvxids)
 		int			pgprocno = arrayP->pgprocnos[index];
 		PGPROC	   *proc = &allProcs[pgprocno];
 
-		if (proc->delayChkpt)
+		if ((proc->delayChkpt & type) != 0)
 		{
 			VirtualTransactionId vxid;
 
@@ -3101,12 +3110,14 @@ GetVirtualXIDsDelayingChkpt(int *nvxids)
  * those numbers should be small enough for it not to be a problem.
  */
 bool
-HaveVirtualXIDsDelayingChkpt(VirtualTransactionId *vxids, int nvxids)
+HaveVirtualXIDsDelayingChkpt(VirtualTransactionId *vxids, int nvxids, int type)
 {
 	bool		result = false;
 	ProcArrayStruct *arrayP = procArray;
 	int			index;
 
+	Assert(type != 0);
+
 	LWLockAcquire(ProcArrayLock, LW_SHARED);
 
 	for (index = 0; index < arrayP->numProcs; index++)
@@ -3117,7 +3128,8 @@ HaveVirtualXIDsDelayingChkpt(VirtualTransactionId *vxids, int nvxids)
 
 		GET_VXID_FROM_PGPROC(vxid, *proc);
 
-		if (proc->delayChkpt && VirtualTransactionIdIsValid(vxid))
+		if ((proc->delayChkpt & type) != 0 &&
+			VirtualTransactionIdIsValid(vxid))
 		{
 			int			i;