Keep WAL segments by slot's flushed restart LSN

The patch fixes the issue with unexpected removal of old WAL segments
after checkpoint followed by immediate restart. The issue occurs when a
slot is advanced after the start of checkpoint and before old WAL
segments removal at end of 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 oldest LSN for WAL segments removal at the end of
checkpoint. This idea was proposed by Tomas Vondra in the discussion.

Discussion:
https://www.postgresql.org/message-id/flat/1d12d2-67235980-35-19a406a0%4063439497

Author: Vitaly Davydov

src/backend/access/transam/xlog.c

@@ -677,7 +677,8 @@ 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,
@@ -7087,6 +7088,7 @@ CreateCheckPoint(int flags)
 	VirtualTransactionId *vxids;
 	int			nvxids;
 	int			oldXLogAllowed = 0;
+	XLogRecPtr	slotsMinReqLSN;
 
 	/*
 	 * An end-of-recovery checkpoint is really a shutdown checkpoint, just
@@ -7315,6 +7317,11 @@ CreateCheckPoint(int flags)
 	 */
 	END_CRIT_SECTION();
 
+	/*
+	 * Get the current minimum LSN to be used later in WAL segments cleanup.
+	 */
+	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
@@ -7507,17 +7514,20 @@ 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 | RS_INVAL_IDLE_TIMEOUT,
 										   _logSegNo, InvalidOid,
 										   InvalidTransactionId))
 	{
+		slotsMinReqLSN = XLogGetReplicationSlotMinimumLSN();
+		CheckPointReplicationSlots(shutdown);
+
 		/*
 		 * 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,
@@ -7792,6 +7802,7 @@ CreateRestartPoint(int flags)
 	XLogRecPtr	endptr;
 	XLogSegNo	_logSegNo;
 	TimestampTz xtime;
+	XLogRecPtr	slotsMinReqLSN;
 
 	/* Concurrent checkpoint/restartpoint cannot happen */
 	Assert(!IsUnderPostmaster || MyBackendType == B_CHECKPOINTER);
@@ -7874,6 +7885,11 @@ CreateRestartPoint(int flags)
 	MemSet(&CheckpointStats, 0, sizeof(CheckpointStats));
 	CheckpointStats.ckpt_start_t = GetCurrentTimestamp();
 
+	/*
+	 * Get the current minimum LSN to be used later in WAL segments cleanup.
+	 */
+	slotsMinReqLSN = XLogGetReplicationSlotMinimumLSN();
+
 	if (log_checkpoints)
 		LogCheckpointStart(flags, true);
 
@@ -7962,17 +7978,20 @@ 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 | RS_INVAL_IDLE_TIMEOUT,
 										   _logSegNo, InvalidOid,
 										   InvalidTransactionId))
 	{
+		slotsMinReqLSN = XLogGetReplicationSlotMinimumLSN();
+		CheckPointReplicationSlots(flags & CHECKPOINT_IS_SHUTDOWN);
+
 		/*
 		 * 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--;
 
@@ -8067,6 +8086,7 @@ 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
@@ -8080,8 +8100,9 @@ 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
@@ -8142,7 +8163,7 @@ 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;
@@ -8155,7 +8176,7 @@ 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);