Keep WAL segments by the flushed value of the slot's restart LSN

akorotkov · akorotkov · commit cea8f2c3e44b · 2025-06-14T03:53:18.000+03:00
The patch fixes the issue with the unexpected removal of old WAL segments after checkpoint, followed by an immediate restart. The issue occurs when a slot is advanced after the start of the checkpoint and before old WAL segments are removed at the end of the checkpoint. The idea of the patch is to get the minimal restart_lsn at the beginning of checkpoint (or restart point) creation and use this value when calculating the oldest LSN for WAL segments removal at the end of checkpoint. This idea was proposed by Tomas Vondra in the discussion. Unlike 291221c46575, this fix doesn't affect ABI and is intended for back branches. Discussion: https://postgr.es/m/flat/1d12d2-67235980-35-19a406a0%4063439497 Author: Vitaly Davydov <v.davydov@postgrespro.ru> Reviewed-by: Tomas Vondra <tomas@vondra.me> Reviewed-by: Alexander Korotkov <aekorotkov@gmail.com> Reviewed-by: Amit Kapila <amit.kapila16@gmail.com> Backpatch-through: 13
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
@@ -650,7 +650,8 @@ static XLogRecPtr CreateOverwriteContrecordRecord(XLogRecPtr aborted_lsn,
 												  XLogRecPtr pagePtr,
 												  TimeLineID newTLI);
 static void CheckPointGuts(XLogRecPtr checkPointRedo, int flags);
-static void KeepLogSeg(XLogRecPtr recptr, XLogSegNo *logSegNo);
+static void KeepLogSeg(XLogRecPtr recptr, XLogRecPtr slotsMinLSN,
+					   XLogSegNo *logSegNo);
 static XLogRecPtr XLogGetReplicationSlotMinimumLSN(void);
 
 static void AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli,
@@ -6492,6 +6493,7 @@ CreateCheckPoint(int flags)
 	VirtualTransactionId *vxids;
 	int			nvxids;
 	int			oldXLogAllowed = 0;
+	XLogRecPtr	slotsMinReqLSN;
 
 	/*
 	 * An end-of-recovery checkpoint is really a shutdown checkpoint, just
@@ -6693,6 +6695,15 @@ CreateCheckPoint(int flags)
 	 */
 	END_CRIT_SECTION();
 
+	/*
+	 * Get the current minimum LSN to be used later in the WAL segment
+	 * cleanup.  We may clean up only WAL segments, which are not needed
+	 * according to synchronized LSNs of replication slots.  The slot's LSN
+	 * might be advanced concurrently, so we call this before
+	 * CheckPointReplicationSlots() synchronizes replication slots.
+	 */
+	slotsMinReqLSN = XLogGetReplicationSlotMinimumLSN();
+
 	/*
 	 * In some cases there are groups of actions that must all occur on one
 	 * side or the other of a checkpoint record. Before flushing the
@@ -6858,17 +6869,25 @@ CreateCheckPoint(int flags)
 	 * prevent the disk holding the xlog from growing full.
 	 */
 	XLByteToSeg(RedoRecPtr, _logSegNo, wal_segment_size);
-	KeepLogSeg(recptr, &_logSegNo);
+	KeepLogSeg(recptr, slotsMinReqLSN, &_logSegNo);
 	if (InvalidateObsoleteReplicationSlots(RS_INVAL_WAL_REMOVED,
 										   _logSegNo, InvalidOid,
 										   InvalidTransactionId))
 	{
+		/*
+		 * Recalculate the current minimum LSN to be used in the WAL segment
+		 * cleanup.  Then, we must synchronize the replication slots again in
+		 * order to make this LSN safe to use.
+		 */
+		slotsMinReqLSN = XLogGetReplicationSlotMinimumLSN();
+		CheckPointReplicationSlots();
+
 		/*
 		 * Some slots have been invalidated; recalculate the old-segment
 		 * horizon, starting again from RedoRecPtr.
 		 */
 		XLByteToSeg(RedoRecPtr, _logSegNo, wal_segment_size);
-		KeepLogSeg(recptr, &_logSegNo);
+		KeepLogSeg(recptr, slotsMinReqLSN, &_logSegNo);
 	}
 	_logSegNo--;
 	RemoveOldXlogFiles(_logSegNo, RedoRecPtr, recptr,
@@ -7140,6 +7159,7 @@ CreateRestartPoint(int flags)
 	XLogRecPtr	endptr;
 	XLogSegNo	_logSegNo;
 	TimestampTz xtime;
+	XLogRecPtr	slotsMinReqLSN;
 
 	/* Concurrent checkpoint/restartpoint cannot happen */
 	Assert(!IsUnderPostmaster || MyBackendType == B_CHECKPOINTER);
@@ -7222,6 +7242,15 @@ CreateRestartPoint(int flags)
 	MemSet(&CheckpointStats, 0, sizeof(CheckpointStats));
 	CheckpointStats.ckpt_start_t = GetCurrentTimestamp();
 
+	/*
+	 * Get the current minimum LSN to be used later in the WAL segment
+	 * cleanup.  We may clean up only WAL segments, which are not needed
+	 * according to synchronized LSNs of replication slots.  The slot's LSN
+	 * might be advanced concurrently, so we call this before
+	 * CheckPointReplicationSlots() synchronizes replication slots.
+	 */
+	slotsMinReqLSN = XLogGetReplicationSlotMinimumLSN();
+
 	if (log_checkpoints)
 		LogCheckpointStart(flags, true);
 
@@ -7304,17 +7333,25 @@ CreateRestartPoint(int flags)
 	receivePtr = GetWalRcvFlushRecPtr(NULL, NULL);
 	replayPtr = GetXLogReplayRecPtr(&replayTLI);
 	endptr = (receivePtr < replayPtr) ? replayPtr : receivePtr;
-	KeepLogSeg(endptr, &_logSegNo);
+	KeepLogSeg(endptr, slotsMinReqLSN, &_logSegNo);
 	if (InvalidateObsoleteReplicationSlots(RS_INVAL_WAL_REMOVED,
 										   _logSegNo, InvalidOid,
 										   InvalidTransactionId))
 	{
+		/*
+		 * Recalculate the current minimum LSN to be used in the WAL segment
+		 * cleanup.  Then, we must synchronize the replication slots again in
+		 * order to make this LSN safe to use.
+		 */
+		slotsMinReqLSN = XLogGetReplicationSlotMinimumLSN();
+		CheckPointReplicationSlots();
+
 		/*
 		 * Some slots have been invalidated; recalculate the old-segment
 		 * horizon, starting again from RedoRecPtr.
 		 */
 		XLByteToSeg(RedoRecPtr, _logSegNo, wal_segment_size);
-		KeepLogSeg(endptr, &_logSegNo);
+		KeepLogSeg(endptr, slotsMinReqLSN, &_logSegNo);
 	}
 	_logSegNo--;
 
@@ -7409,6 +7446,7 @@ GetWALAvailability(XLogRecPtr targetLSN)
 	XLogSegNo	oldestSegMaxWalSize;	/* oldest segid kept by max_wal_size */
 	XLogSegNo	oldestSlotSeg;	/* oldest segid kept by slot */
 	uint64		keepSegs;
+	XLogRecPtr	slotsMinReqLSN;
 
 	/*
 	 * slot does not reserve WAL. Either deactivated, or has never been active
@@ -7422,8 +7460,9 @@ GetWALAvailability(XLogRecPtr targetLSN)
 	 * oldestSlotSeg to the current segment.
 	 */
 	currpos = GetXLogWriteRecPtr();
+	slotsMinReqLSN = XLogGetReplicationSlotMinimumLSN();
 	XLByteToSeg(currpos, oldestSlotSeg, wal_segment_size);
-	KeepLogSeg(currpos, &oldestSlotSeg);
+	KeepLogSeg(currpos, slotsMinReqLSN, &oldestSlotSeg);
 
 	/*
 	 * Find the oldest extant segment file. We get 1 until checkpoint removes
@@ -7484,7 +7523,7 @@ GetWALAvailability(XLogRecPtr targetLSN)
  * invalidation is optionally done here, instead.
  */
 static void
-KeepLogSeg(XLogRecPtr recptr, XLogSegNo *logSegNo)
+KeepLogSeg(XLogRecPtr recptr, XLogRecPtr slotsMinReqLSN, XLogSegNo *logSegNo)
 {
 	XLogSegNo	currSegNo;
 	XLogSegNo	segno;
@@ -7497,7 +7536,7 @@ KeepLogSeg(XLogRecPtr recptr, XLogSegNo *logSegNo)
 	 * Calculate how many segments are kept by slots first, adjusting for
 	 * max_slot_wal_keep_size.
 	 */
-	keep = XLogGetReplicationSlotMinimumLSN();
+	keep = slotsMinReqLSN;
 	if (keep != InvalidXLogRecPtr && keep < recptr)
 	{
 		XLByteToSeg(keep, segno, wal_segment_size);
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
@@ -1880,7 +1880,15 @@ LogicalConfirmReceivedLocation(XLogRecPtr lsn)
 
 		SpinLockRelease(&MyReplicationSlot->mutex);
 
-		/* first write new xmin to disk, so we know what's up after a crash */
+		/*
+		 * First, write new xmin and restart_lsn to disk so we know what's up
+		 * after a crash.  Even when we do this, the checkpointer can see the
+		 * updated restart_lsn value in the shared memory; then, a crash can
+		 * happen before we manage to write that value to the disk.  Thus,
+		 * checkpointer still needs to make special efforts to keep WAL
+		 * segments required by the restart_lsn written to the disk.  See
+		 * CreateCheckPoint() and CreateRestartPoint() for details.
+		 */
 		if (updated_xmin || updated_restart)
 		{
 			ReplicationSlotMarkDirty();
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
@@ -2071,6 +2071,10 @@ PhysicalConfirmReceivedLocation(XLogRecPtr lsn)
 	 * be energy wasted - the worst thing lost information could cause here is
 	 * to give wrong information in a statistics view - we'll just potentially
 	 * be more conservative in removing files.
+	 *
+	 * Checkpointer makes special efforts to keep the WAL segments required by
+	 * the restart_lsn written to the disk. See CreateCheckPoint() and
+	 * CreateRestartPoint() for details.
 	 */
 }
 
