v4-0001-Keep-WAL-segments-by-the-flushed-value-of-the-slo.patch
application/x-patch
Filename: v4-0001-Keep-WAL-segments-by-the-flushed-value-of-the-slo.patch
Type: application/x-patch
Part: 0
Patch
Same data as JSON:
GET /api/v1/attachments/:id/patch
the parsed metadata as JSON — format, series position, per-file stats; never the diff bytes.
API reference →
Format: format-patch
Series: patch v4-0001
Subject: Keep WAL segments by the flushed value of the slot's restart LSN
| File | + | − |
|---|---|---|
| src/backend/access/transam/xlog.c | 29 | 8 |
From c409a441be6487063d49c2671d3a3aecb9ba6994 Mon Sep 17 00:00:00 2001
From: Vitaly Davydov <v.davydov@postgrespro.ru>
Date: Wed, 30 Apr 2025 14:09:21 +0300
Subject: [PATCH v4 1/3] Keep WAL segments by the flushed value of the slot's
restart LSN
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.
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>
Backpatch-through: 13
---
src/backend/access/transam/xlog.c | 37 ++++++++++++++++++++++++-------
1 file changed, 29 insertions(+), 8 deletions(-)
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 1914859b2ee..30ae65fce53 100644
--- a/src/backend/access/transam/xlog.c
+++ b/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
@@ -7503,17 +7510,20 @@ 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,
@@ -7788,6 +7798,7 @@ CreateRestartPoint(int flags)
XLogRecPtr endptr;
XLogSegNo _logSegNo;
TimestampTz xtime;
+ XLogRecPtr slotsMinReqLSN;
/* Concurrent checkpoint/restartpoint cannot happen */
Assert(!IsUnderPostmaster || MyBackendType == B_CHECKPOINTER);
@@ -7870,6 +7881,11 @@ 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);
@@ -7958,17 +7974,20 @@ 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--;
@@ -8063,6 +8082,7 @@ 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
@@ -8076,8 +8096,9 @@ 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
@@ -8138,7 +8159,7 @@ 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;
@@ -8151,7 +8172,7 @@ 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);
--
2.39.5 (Apple Git-154)