agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v12] Use only xlogreader.c:WALRead()
55+ messages / 1 participants
[nested] [flat]

* [PATCH v12] Use only xlogreader.c:WALRead()
@ 2019-11-12 10:51  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2019-11-12 10:51 UTC (permalink / raw)

---
 src/backend/access/transam/xlogreader.c | 104 ++++++++-
 src/backend/access/transam/xlogutils.c  | 207 ++++++----------
 src/backend/replication/walsender.c     | 298 ++++++++++--------------
 src/bin/pg_waldump/pg_waldump.c         | 164 ++++---------
 src/include/access/xlogreader.h         |  39 +++-
 src/include/access/xlogutils.h          |   2 +
 6 files changed, 383 insertions(+), 431 deletions(-)

diff --git a/src/backend/access/transam/xlogreader.c b/src/backend/access/transam/xlogreader.c
index 7f24f0cb95..3692c46f43 100644
--- a/src/backend/access/transam/xlogreader.c
+++ b/src/backend/access/transam/xlogreader.c
@@ -17,6 +17,8 @@
  */
 #include "postgres.h"
 
+#include <unistd.h>
+
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogreader.h"
@@ -27,6 +29,7 @@
 
 #ifndef FRONTEND
 #include "miscadmin.h"
+#include "pgstat.h"
 #include "utils/memutils.h"
 #endif
 
@@ -208,7 +211,6 @@ WALOpenSegmentInit(WALOpenSegment *seg, WALSegmentContext *segcxt,
 {
 	seg->ws_file = -1;
 	seg->ws_segno = 0;
-	seg->ws_off = 0;
 	seg->ws_tli = 0;
 
 	segcxt->ws_segsize = segsize;
@@ -295,8 +297,7 @@ XLogReadRecord(XLogReaderState *state, XLogRecPtr RecPtr, char **errormsg)
 	 * byte to cover the whole record header, or at least the part of it that
 	 * fits on the same page.
 	 */
-	readOff = ReadPageInternal(state,
-							   targetPagePtr,
+	readOff = ReadPageInternal(state, targetPagePtr,
 							   Min(targetRecOff + SizeOfXLogRecord, XLOG_BLCKSZ));
 	if (readOff < 0)
 		goto err;
@@ -556,7 +557,7 @@ ReadPageInternal(XLogReaderState *state, XLogRecPtr pageptr, int reqLen)
 
 	/* check whether we have all the requested data already */
 	if (targetSegNo == state->seg.ws_segno &&
-		targetPageOff == state->seg.ws_off && reqLen <= state->readLen)
+		targetPageOff == state->segoff && reqLen <= state->readLen)
 		return state->readLen;
 
 	/*
@@ -627,7 +628,7 @@ ReadPageInternal(XLogReaderState *state, XLogRecPtr pageptr, int reqLen)
 
 	/* update read state information */
 	state->seg.ws_segno = targetSegNo;
-	state->seg.ws_off = targetPageOff;
+	state->segoff = targetPageOff;
 	state->readLen = readLen;
 
 	return readLen;
@@ -644,7 +645,7 @@ static void
 XLogReaderInvalReadState(XLogReaderState *state)
 {
 	state->seg.ws_segno = 0;
-	state->seg.ws_off = 0;
+	state->segoff = 0;
 	state->readLen = 0;
 }
 
@@ -1015,6 +1016,97 @@ out:
 
 #endif							/* FRONTEND */
 
+/*
+ * Read 'count' bytes into 'buf', starting at location 'startptr', from WAL
+ * fetched from timeline 'tli'.
+ *
+ * 'seg/segcxt' identify the last segment used.  'openSegment' is a callback
+ * to open the next segment, if necessary.
+ *
+ * Returns true if succeeded, false if an error occurs, in which case
+ * 'errinfo' receives error details.
+ *
+ * XXX probably this should be improved to suck data directly from the
+ * WAL buffers when possible.
+ */
+bool
+WALRead(char *buf, XLogRecPtr startptr, Size count, TimeLineID tli,
+		WALOpenSegment *seg, WALSegmentContext *segcxt,
+		WALSegmentOpen openSegment, WALReadError *errinfo)
+{
+	char	   *p;
+	XLogRecPtr	recptr;
+	Size		nbytes;
+
+	p = buf;
+	recptr = startptr;
+	nbytes = count;
+
+	while (nbytes > 0)
+	{
+		uint32		startoff;
+		int			segbytes;
+		int			readbytes;
+
+		startoff = XLogSegmentOffset(recptr, segcxt->ws_segsize);
+
+		if (seg->ws_file < 0 ||
+			!XLByteInSeg(recptr, seg->ws_segno, segcxt->ws_segsize) ||
+			tli != seg->ws_tli)
+		{
+			XLogSegNo	nextSegNo;
+
+			/* Switch to another logfile segment */
+			if (seg->ws_file >= 0)
+				close(seg->ws_file);
+
+			XLByteToSeg(recptr, nextSegNo, segcxt->ws_segsize);
+
+			/* Open the next segment in the caller's way. */
+			seg->ws_file = openSegment(nextSegNo, segcxt, &tli);
+
+			/* Update the current segment info. */
+			seg->ws_tli = tli;
+			seg->ws_segno = nextSegNo;
+		}
+
+		/* How many bytes are within this segment? */
+		if (nbytes > (segcxt->ws_segsize - startoff))
+			segbytes = segcxt->ws_segsize - startoff;
+		else
+			segbytes = nbytes;
+
+#ifndef FRONTEND
+		pgstat_report_wait_start(WAIT_EVENT_WAL_READ);
+#endif
+
+		/* Reset errno first; eases reporting non-errno-affecting errors */
+		errno = 0;
+		readbytes = pg_pread(seg->ws_file, p, segbytes, (off_t) startoff);
+
+#ifndef FRONTEND
+		pgstat_report_wait_end();
+#endif
+
+		if (readbytes <= 0)
+		{
+			errinfo->wre_errno = errno;
+			errinfo->wre_req = segbytes;
+			errinfo->wre_read = readbytes;
+			errinfo->wre_off = startoff;
+			errinfo->wre_seg = *seg;
+			return false;
+		}
+
+		/* Update state for read */
+		recptr += readbytes;
+		nbytes -= readbytes;
+		p += readbytes;
+	}
+
+	return true;
+}
+
 /* ----------------------------------------
  * Functions for decoding the data and block references in a record.
  * ----------------------------------------
diff --git a/src/backend/access/transam/xlogutils.c b/src/backend/access/transam/xlogutils.c
index 5f1e5ba75d..9836b6446a 100644
--- a/src/backend/access/transam/xlogutils.c
+++ b/src/backend/access/transam/xlogutils.c
@@ -639,128 +639,6 @@ XLogTruncateRelation(RelFileNode rnode, ForkNumber forkNum,
 	forget_invalid_pages(rnode, forkNum, nblocks);
 }
 
-/*
- * Read 'count' bytes from WAL into 'buf', starting at location 'startptr'
- * in timeline 'tli'.
- *
- * Will open, and keep open, one WAL segment stored in the static file
- * descriptor 'sendFile'. This means if XLogRead is used once, there will
- * always be one descriptor left open until the process ends, but never
- * more than one.
- *
- * XXX This is very similar to pg_waldump's XLogDumpXLogRead and to XLogRead
- * in walsender.c but for small differences (such as lack of elog() in
- * frontend).  Probably these should be merged at some point.
- */
-static void
-XLogRead(char *buf, int segsize, TimeLineID tli, XLogRecPtr startptr,
-		 Size count)
-{
-	char	   *p;
-	XLogRecPtr	recptr;
-	Size		nbytes;
-
-	/* state maintained across calls */
-	static int	sendFile = -1;
-	static XLogSegNo sendSegNo = 0;
-	static TimeLineID sendTLI = 0;
-	static uint32 sendOff = 0;
-
-	Assert(segsize == wal_segment_size);
-
-	p = buf;
-	recptr = startptr;
-	nbytes = count;
-
-	while (nbytes > 0)
-	{
-		uint32		startoff;
-		int			segbytes;
-		int			readbytes;
-
-		startoff = XLogSegmentOffset(recptr, segsize);
-
-		/* Do we need to switch to a different xlog segment? */
-		if (sendFile < 0 || !XLByteInSeg(recptr, sendSegNo, segsize) ||
-			sendTLI != tli)
-		{
-			char		path[MAXPGPATH];
-
-			if (sendFile >= 0)
-				close(sendFile);
-
-			XLByteToSeg(recptr, sendSegNo, segsize);
-
-			XLogFilePath(path, tli, sendSegNo, segsize);
-
-			sendFile = BasicOpenFile(path, O_RDONLY | PG_BINARY);
-
-			if (sendFile < 0)
-			{
-				if (errno == ENOENT)
-					ereport(ERROR,
-							(errcode_for_file_access(),
-							 errmsg("requested WAL segment %s has already been removed",
-									path)));
-				else
-					ereport(ERROR,
-							(errcode_for_file_access(),
-							 errmsg("could not open file \"%s\": %m",
-									path)));
-			}
-			sendOff = 0;
-			sendTLI = tli;
-		}
-
-		/* Need to seek in the file? */
-		if (sendOff != startoff)
-		{
-			if (lseek(sendFile, (off_t) startoff, SEEK_SET) < 0)
-			{
-				char		path[MAXPGPATH];
-				int			save_errno = errno;
-
-				XLogFilePath(path, tli, sendSegNo, segsize);
-				errno = save_errno;
-				ereport(ERROR,
-						(errcode_for_file_access(),
-						 errmsg("could not seek in log segment %s to offset %u: %m",
-								path, startoff)));
-			}
-			sendOff = startoff;
-		}
-
-		/* How many bytes are within this segment? */
-		if (nbytes > (segsize - startoff))
-			segbytes = segsize - startoff;
-		else
-			segbytes = nbytes;
-
-		pgstat_report_wait_start(WAIT_EVENT_WAL_READ);
-		readbytes = read(sendFile, p, segbytes);
-		pgstat_report_wait_end();
-		if (readbytes <= 0)
-		{
-			char		path[MAXPGPATH];
-			int			save_errno = errno;
-
-			XLogFilePath(path, tli, sendSegNo, segsize);
-			errno = save_errno;
-			ereport(ERROR,
-					(errcode_for_file_access(),
-					 errmsg("could not read from log segment %s, offset %u, length %lu: %m",
-							path, sendOff, (unsigned long) segbytes)));
-		}
-
-		/* Update state for read */
-		recptr += readbytes;
-
-		sendOff += readbytes;
-		nbytes -= readbytes;
-		p += readbytes;
-	}
-}
-
 /*
  * Determine which timeline to read an xlog page from and set the
  * XLogReaderState's currTLI to that timeline ID.
@@ -802,8 +680,8 @@ XLogRead(char *buf, int segsize, TimeLineID tli, XLogRecPtr startptr,
 void
 XLogReadDetermineTimeline(XLogReaderState *state, XLogRecPtr wantPage, uint32 wantLength)
 {
-	const XLogRecPtr lastReadPage = state->seg.ws_segno *
-	state->segcxt.ws_segsize + state->seg.ws_off;
+	const XLogRecPtr lastReadPage = (state->seg.ws_segno *
+									 state->segcxt.ws_segsize + state->segoff);
 
 	Assert(wantPage != InvalidXLogRecPtr && wantPage % XLOG_BLCKSZ == 0);
 	Assert(wantLength <= XLOG_BLCKSZ);
@@ -896,6 +774,36 @@ XLogReadDetermineTimeline(XLogReaderState *state, XLogRecPtr wantPage, uint32 wa
 	}
 }
 
+/*
+ * Callback for WALRead() to open the next segment.
+ */
+static int
+wal_segment_open(XLogSegNo nextSegNo, WALSegmentContext *segcxt,
+				 TimeLineID *tli_p)
+{
+	TimeLineID	tli = *tli_p;
+	char		path[MAXPGPATH];
+	int			fd;
+
+	XLogFilePath(path, tli, nextSegNo, segcxt->ws_segsize);
+	fd = BasicOpenFile(path, O_RDONLY | PG_BINARY);
+	if (fd >= 0)
+		return fd;
+
+	if (errno == ENOENT)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("requested WAL segment %s has already been removed",
+						path)));
+	else
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m",
+						path)));
+
+	return -1;					/* keep compiler quiet */
+}
+
 /*
  * read_page callback for reading local xlog files
  *
@@ -913,7 +821,9 @@ read_local_xlog_page(XLogReaderState *state, XLogRecPtr targetPagePtr,
 {
 	XLogRecPtr	read_upto,
 				loc;
+	TimeLineID	tli;
 	int			count;
+	WALReadError errinfo;
 
 	loc = targetPagePtr + reqLen;
 
@@ -932,7 +842,7 @@ read_local_xlog_page(XLogReaderState *state, XLogRecPtr targetPagePtr,
 			read_upto = GetFlushRecPtr();
 		else
 			read_upto = GetXLogReplayRecPtr(&ThisTimeLineID);
-		state->seg.ws_tli = ThisTimeLineID;
+		tli = ThisTimeLineID;
 
 		/*
 		 * Check which timeline to get the record from.
@@ -982,14 +892,14 @@ read_local_xlog_page(XLogReaderState *state, XLogRecPtr targetPagePtr,
 			read_upto = state->currTLIValidUntil;
 
 			/*
-			 * Setting ws_tli to our wanted record's TLI is slightly wrong;
-			 * the page might begin on an older timeline if it contains a
-			 * timeline switch, since its xlog segment will have been copied
-			 * from the prior timeline. This is pretty harmless though, as
-			 * nothing cares so long as the timeline doesn't go backwards.  We
-			 * should read the page header instead; FIXME someday.
+			 * Setting tli to our wanted record's TLI is slightly wrong; the
+			 * page might begin on an older timeline if it contains a timeline
+			 * switch, since its xlog segment will have been copied from the
+			 * prior timeline. This is pretty harmless though, as nothing
+			 * cares so long as the timeline doesn't go backwards.  We should
+			 * read the page header instead; FIXME someday.
 			 */
-			state->seg.ws_tli = state->currTLI;
+			tli = state->currTLI;
 
 			/* No need to wait on a historical timeline */
 			break;
@@ -1020,9 +930,38 @@ read_local_xlog_page(XLogReaderState *state, XLogRecPtr targetPagePtr,
 	 * as 'count', read the whole page anyway. It's guaranteed to be
 	 * zero-padded up to the page boundary if it's incomplete.
 	 */
-	XLogRead(cur_page, state->segcxt.ws_segsize, state->seg.ws_tli, targetPagePtr,
-			 XLOG_BLCKSZ);
+	if (!WALRead(cur_page, targetPagePtr, XLOG_BLCKSZ, tli, &state->seg,
+				 &state->segcxt, wal_segment_open, &errinfo))
+		WALReadRaiseError(&errinfo);
 
 	/* number of valid bytes in the buffer */
 	return count;
 }
+
+/*
+ * Backend-specific convenience code to handle read errors encountered by
+ * WALRead().
+ */
+void
+WALReadRaiseError(WALReadError *errinfo)
+{
+	WALOpenSegment *seg = &errinfo->wre_seg;
+	char	   *fname = XLogFileNameP(seg->ws_tli, seg->ws_segno);
+
+	if (errinfo->wre_read < 0)
+	{
+		errno = errinfo->wre_errno;
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not read from log segment %s, offset %u, length %zu: %m",
+						fname, errinfo->wre_off, (Size) errinfo->wre_req)));
+	}
+	else if (errinfo->wre_read == 0)
+	{
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_CORRUPTED),
+				 errmsg("could not read from log segment %s, offset %u: read %d of %zu",
+						fname, errinfo->wre_off, errinfo->wre_read,
+						(Size) errinfo->wre_req)));
+	}
+}
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index fa75872877..c124f59435 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -248,8 +248,9 @@ static void LagTrackerWrite(XLogRecPtr lsn, TimestampTz local_flush_time);
 static TimeOffset LagTrackerRead(int head, XLogRecPtr lsn, TimestampTz now);
 static bool TransactionIdInRecentPast(TransactionId xid, uint32 epoch);
 
+static int	WalSndSegmentOpen(XLogSegNo nextSegNo, WALSegmentContext *segcxt,
+							  TimeLineID *tli_p);
 static void UpdateSpillStats(LogicalDecodingContext *ctx);
-static void XLogRead(WALSegmentContext *segcxt, char *buf, XLogRecPtr startptr, Size count);
 
 
 /* Initialize walsender process before entering the main command loop */
@@ -767,6 +768,8 @@ logical_read_xlog_page(XLogReaderState *state, XLogRecPtr targetPagePtr, int req
 {
 	XLogRecPtr	flushptr;
 	int			count;
+	WALReadError errinfo;
+	XLogSegNo	segno;
 
 	XLogReadDetermineTimeline(state, targetPagePtr, reqLen);
 	sendTimeLineIsHistoric = (state->currTLI != ThisTimeLineID);
@@ -787,7 +790,27 @@ logical_read_xlog_page(XLogReaderState *state, XLogRecPtr targetPagePtr, int req
 		count = flushptr - targetPagePtr;	/* part of the page available */
 
 	/* now actually read the data, we know it's there */
-	XLogRead(sendCxt, cur_page, targetPagePtr, XLOG_BLCKSZ);
+	if (!WALRead(cur_page,
+				 targetPagePtr,
+				 XLOG_BLCKSZ,
+				 sendSeg->ws_tli,	/* Pass the current TLI because only
+									 * WalSndSegmentOpen controls whether new
+									 * TLI is needed. */
+				 sendSeg,
+				 sendCxt,
+				 WalSndSegmentOpen,
+				 &errinfo))
+		WALReadRaiseError(&errinfo);
+
+	/*
+	 * After reading into the buffer, check that what we read was valid. We do
+	 * this after reading, because even though the segment was present when we
+	 * opened it, it might get recycled or removed while we read it. The
+	 * read() succeeds in that case, but the data we tried to read might
+	 * already have been overwritten with new WAL records.
+	 */
+	XLByteToSeg(targetPagePtr, segno, sendCxt->ws_segsize);
+	CheckXLogRemoved(segno, sendSeg->ws_tli);
 
 	return count;
 }
@@ -2361,188 +2384,69 @@ WalSndKill(int code, Datum arg)
 }
 
 /*
- * Read 'count' bytes from WAL into 'buf', starting at location 'startptr'
- *
- * XXX probably this should be improved to suck data directly from the
- * WAL buffers when possible.
- *
- * Will open, and keep open, one WAL segment stored in the global file
- * descriptor sendFile. This means if XLogRead is used once, there will
- * always be one descriptor left open until the process ends, but never
- * more than one.
+ * Callback for XLogRead() to open the next segment.
  */
-static void
-XLogRead(WALSegmentContext *segcxt, char *buf, XLogRecPtr startptr, Size count)
+int
+WalSndSegmentOpen(XLogSegNo nextSegNo, WALSegmentContext *segcxt,
+				  TimeLineID *tli_p)
 {
-	char	   *p;
-	XLogRecPtr	recptr;
-	Size		nbytes;
-	XLogSegNo	segno;
+	char		path[MAXPGPATH];
+	int			fd;
 
-retry:
-	p = buf;
-	recptr = startptr;
-	nbytes = count;
-
-	while (nbytes > 0)
+	/*-------
+	 * When reading from a historic timeline, and there is a timeline switch
+	 * within this segment, read from the WAL segment belonging to the new
+	 * timeline.
+	 *
+	 * For example, imagine that this server is currently on timeline 5, and
+	 * we're streaming timeline 4. The switch from timeline 4 to 5 happened at
+	 * 0/13002088. In pg_wal, we have these files:
+	 *
+	 * ...
+	 * 000000040000000000000012
+	 * 000000040000000000000013
+	 * 000000050000000000000013
+	 * 000000050000000000000014
+	 * ...
+	 *
+	 * In this situation, when requested to send the WAL from segment 0x13, on
+	 * timeline 4, we read the WAL from file 000000050000000000000013. Archive
+	 * recovery prefers files from newer timelines, so if the segment was
+	 * restored from the archive on this server, the file belonging to the old
+	 * timeline, 000000040000000000000013, might not exist. Their contents are
+	 * equal up to the switchpoint, because at a timeline switch, the used
+	 * portion of the old segment is copied to the new file.  -------
+	 */
+	*tli_p = sendTimeLine;
+	if (sendTimeLineIsHistoric)
 	{
-		uint32		startoff;
-		int			segbytes;
-		int			readbytes;
+		XLogSegNo	endSegNo;
 
-		startoff = XLogSegmentOffset(recptr, segcxt->ws_segsize);
-
-		if (sendSeg->ws_file < 0 ||
-			!XLByteInSeg(recptr, sendSeg->ws_segno, segcxt->ws_segsize))
-		{
-			char		path[MAXPGPATH];
-
-			/* Switch to another logfile segment */
-			if (sendSeg->ws_file >= 0)
-				close(sendSeg->ws_file);
-
-			XLByteToSeg(recptr, sendSeg->ws_segno, segcxt->ws_segsize);
-
-			/*-------
-			 * When reading from a historic timeline, and there is a timeline
-			 * switch within this segment, read from the WAL segment belonging
-			 * to the new timeline.
-			 *
-			 * For example, imagine that this server is currently on timeline
-			 * 5, and we're streaming timeline 4. The switch from timeline 4
-			 * to 5 happened at 0/13002088. In pg_wal, we have these files:
-			 *
-			 * ...
-			 * 000000040000000000000012
-			 * 000000040000000000000013
-			 * 000000050000000000000013
-			 * 000000050000000000000014
-			 * ...
-			 *
-			 * In this situation, when requested to send the WAL from
-			 * segment 0x13, on timeline 4, we read the WAL from file
-			 * 000000050000000000000013. Archive recovery prefers files from
-			 * newer timelines, so if the segment was restored from the
-			 * archive on this server, the file belonging to the old timeline,
-			 * 000000040000000000000013, might not exist. Their contents are
-			 * equal up to the switchpoint, because at a timeline switch, the
-			 * used portion of the old segment is copied to the new file.
-			 *-------
-			 */
-			sendSeg->ws_tli = sendTimeLine;
-			if (sendTimeLineIsHistoric)
-			{
-				XLogSegNo	endSegNo;
-
-				XLByteToSeg(sendTimeLineValidUpto, endSegNo, segcxt->ws_segsize);
-				if (sendSeg->ws_segno == endSegNo)
-					sendSeg->ws_tli = sendTimeLineNextTLI;
-			}
-
-			XLogFilePath(path, sendSeg->ws_tli, sendSeg->ws_segno, segcxt->ws_segsize);
-
-			sendSeg->ws_file = BasicOpenFile(path, O_RDONLY | PG_BINARY);
-			if (sendSeg->ws_file < 0)
-			{
-				/*
-				 * If the file is not found, assume it's because the standby
-				 * asked for a too old WAL segment that has already been
-				 * removed or recycled.
-				 */
-				if (errno == ENOENT)
-					ereport(ERROR,
-							(errcode_for_file_access(),
-							 errmsg("requested WAL segment %s has already been removed",
-									XLogFileNameP(sendSeg->ws_tli, sendSeg->ws_segno))));
-				else
-					ereport(ERROR,
-							(errcode_for_file_access(),
-							 errmsg("could not open file \"%s\": %m",
-									path)));
-			}
-			sendSeg->ws_off = 0;
-		}
-
-		/* Need to seek in the file? */
-		if (sendSeg->ws_off != startoff)
-		{
-			if (lseek(sendSeg->ws_file, (off_t) startoff, SEEK_SET) < 0)
-				ereport(ERROR,
-						(errcode_for_file_access(),
-						 errmsg("could not seek in log segment %s to offset %u: %m",
-								XLogFileNameP(sendSeg->ws_tli, sendSeg->ws_segno),
-								startoff)));
-			sendSeg->ws_off = startoff;
-		}
-
-		/* How many bytes are within this segment? */
-		if (nbytes > (segcxt->ws_segsize - startoff))
-			segbytes = segcxt->ws_segsize - startoff;
-		else
-			segbytes = nbytes;
-
-		pgstat_report_wait_start(WAIT_EVENT_WAL_READ);
-		readbytes = read(sendSeg->ws_file, p, segbytes);
-		pgstat_report_wait_end();
-		if (readbytes < 0)
-		{
-			ereport(ERROR,
-					(errcode_for_file_access(),
-					 errmsg("could not read from log segment %s, offset %u, length %zu: %m",
-							XLogFileNameP(sendSeg->ws_tli, sendSeg->ws_segno),
-							sendSeg->ws_off, (Size) segbytes)));
-		}
-		else if (readbytes == 0)
-		{
-			ereport(ERROR,
-					(errcode(ERRCODE_DATA_CORRUPTED),
-					 errmsg("could not read from log segment %s, offset %u: read %d of %zu",
-							XLogFileNameP(sendSeg->ws_tli, sendSeg->ws_segno),
-							sendSeg->ws_off, readbytes, (Size) segbytes)));
-		}
-
-		/* Update state for read */
-		recptr += readbytes;
-
-		sendSeg->ws_off += readbytes;
-		nbytes -= readbytes;
-		p += readbytes;
+		XLByteToSeg(sendTimeLineValidUpto, endSegNo, segcxt->ws_segsize);
+		if (sendSeg->ws_segno == endSegNo)
+			*tli_p = sendTimeLineNextTLI;
 	}
 
-	/*
-	 * After reading into the buffer, check that what we read was valid. We do
-	 * this after reading, because even though the segment was present when we
-	 * opened it, it might get recycled or removed while we read it. The
-	 * read() succeeds in that case, but the data we tried to read might
-	 * already have been overwritten with new WAL records.
-	 */
-	XLByteToSeg(startptr, segno, segcxt->ws_segsize);
-	CheckXLogRemoved(segno, ThisTimeLineID);
+	XLogFilePath(path, *tli_p, nextSegNo, segcxt->ws_segsize);
+	fd = BasicOpenFile(path, O_RDONLY | PG_BINARY);
+	if (fd >= 0)
+		return fd;
 
 	/*
-	 * During recovery, the currently-open WAL file might be replaced with the
-	 * file of the same name retrieved from archive. So we always need to
-	 * check what we read was valid after reading into the buffer. If it's
-	 * invalid, we try to open and read the file again.
+	 * If the file is not found, assume it's because the standby asked for a
+	 * too old WAL segment that has already been removed or recycled.
 	 */
-	if (am_cascading_walsender)
-	{
-		WalSnd	   *walsnd = MyWalSnd;
-		bool		reload;
-
-		SpinLockAcquire(&walsnd->mutex);
-		reload = walsnd->needreload;
-		walsnd->needreload = false;
-		SpinLockRelease(&walsnd->mutex);
-
-		if (reload && sendSeg->ws_file >= 0)
-		{
-			close(sendSeg->ws_file);
-			sendSeg->ws_file = -1;
-
-			goto retry;
-		}
-	}
+	if (errno == ENOENT)
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("requested WAL segment %s has already been removed",
+						XLogFileNameP(*tli_p, nextSegNo))));
+	else
+		ereport(ERROR,
+				(errcode_for_file_access(),
+				 errmsg("could not open file \"%s\": %m",
+						path)));
+	return -1;					/* keep compiler quiet */
 }
 
 /*
@@ -2562,6 +2466,8 @@ XLogSendPhysical(void)
 	XLogRecPtr	startptr;
 	XLogRecPtr	endptr;
 	Size		nbytes;
+	XLogSegNo	segno;
+	WALReadError errinfo;
 
 	/* If requested switch the WAL sender to the stopping state. */
 	if (got_STOPPING)
@@ -2777,7 +2683,49 @@ XLogSendPhysical(void)
 	 * calls.
 	 */
 	enlargeStringInfo(&output_message, nbytes);
-	XLogRead(sendCxt, &output_message.data[output_message.len], startptr, nbytes);
+
+retry:
+	if (!WALRead(&output_message.data[output_message.len],
+				 startptr,
+				 nbytes,
+				 sendSeg->ws_tli,	/* Pass the current TLI because only
+									 * WalSndSegmentOpen controls whether new
+									 * TLI is needed. */
+				 sendSeg,
+				 sendCxt,
+				 WalSndSegmentOpen,
+				 &errinfo))
+		WALReadRaiseError(&errinfo);
+
+	/* See logical_read_xlog_page(). */
+	XLByteToSeg(startptr, segno, sendCxt->ws_segsize);
+	CheckXLogRemoved(segno, sendSeg->ws_tli);
+
+	/*
+	 * During recovery, the currently-open WAL file might be replaced with the
+	 * file of the same name retrieved from archive. So we always need to
+	 * check what we read was valid after reading into the buffer. If it's
+	 * invalid, we try to open and read the file again.
+	 */
+	if (am_cascading_walsender)
+	{
+		WalSnd	   *walsnd = MyWalSnd;
+		bool		reload;
+
+		SpinLockAcquire(&walsnd->mutex);
+		reload = walsnd->needreload;
+		walsnd->needreload = false;
+		SpinLockRelease(&walsnd->mutex);
+
+		if (reload && sendSeg->ws_file >= 0)
+		{
+			close(sendSeg->ws_file);
+			sendSeg->ws_file = -1;
+
+			goto retry;
+		}
+	}
+
 	output_message.len += nbytes;
 	output_message.data[output_message.len] = '\0';
 
diff --git a/src/bin/pg_waldump/pg_waldump.c b/src/bin/pg_waldump/pg_waldump.c
index 1524e5eb1e..d5eb2f42f5 100644
--- a/src/bin/pg_waldump/pg_waldump.c
+++ b/src/bin/pg_waldump/pg_waldump.c
@@ -280,137 +280,56 @@ identify_target_directory(char *directory, char *fname)
 	return NULL;				/* not reached */
 }
 
-/*
- * Read count bytes from a segment file in the specified directory, for the
- * given timeline, containing the specified record pointer; store the data in
- * the passed buffer.
- */
-static void
-XLogDumpXLogRead(const char *directory, TimeLineID timeline_id,
-				 XLogRecPtr startptr, char *buf, Size count)
+static int
+WALDumpOpenSegment(XLogSegNo nextSegNo, WALSegmentContext *segcxt,
+				   TimeLineID *tli_p)
 {
-	char	   *p;
-	XLogRecPtr	recptr;
-	Size		nbytes;
+	TimeLineID	tli = *tli_p;
+	char		fname[MAXPGPATH];
+	int			fd;
+	int			tries;
 
-	static int	sendFile = -1;
-	static XLogSegNo sendSegNo = 0;
-	static uint32 sendOff = 0;
+	XLogFileName(fname, tli, nextSegNo, segcxt->ws_segsize);
 
-	p = buf;
-	recptr = startptr;
-	nbytes = count;
-
-	while (nbytes > 0)
+	/*
+	 * In follow mode there is a short period of time after the server has
+	 * written the end of the previous file before the new file is available.
+	 * So we loop for 5 seconds looking for the file to appear before giving
+	 * up.
+	 */
+	for (tries = 0; tries < 10; tries++)
 	{
-		uint32		startoff;
-		int			segbytes;
-		int			readbytes;
-
-		startoff = XLogSegmentOffset(recptr, WalSegSz);
-
-		if (sendFile < 0 || !XLByteInSeg(recptr, sendSegNo, WalSegSz))
+		fd = open_file_in_directory(segcxt->ws_dir, fname);
+		if (fd >= 0)
+			return fd;
+		if (errno == ENOENT)
 		{
-			char		fname[MAXFNAMELEN];
-			int			tries;
-
-			/* Switch to another logfile segment */
-			if (sendFile >= 0)
-				close(sendFile);
-
-			XLByteToSeg(recptr, sendSegNo, WalSegSz);
-
-			XLogFileName(fname, timeline_id, sendSegNo, WalSegSz);
-
-			/*
-			 * In follow mode there is a short period of time after the server
-			 * has written the end of the previous file before the new file is
-			 * available. So we loop for 5 seconds looking for the file to
-			 * appear before giving up.
-			 */
-			for (tries = 0; tries < 10; tries++)
-			{
-				sendFile = open_file_in_directory(directory, fname);
-				if (sendFile >= 0)
-					break;
-				if (errno == ENOENT)
-				{
-					int			save_errno = errno;
-
-					/* File not there yet, try again */
-					pg_usleep(500 * 1000);
-
-					errno = save_errno;
-					continue;
-				}
-				/* Any other error, fall through and fail */
-				break;
-			}
-
-			if (sendFile < 0)
-				fatal_error("could not find file \"%s\": %s",
-							fname, strerror(errno));
-			sendOff = 0;
-		}
-
-		/* Need to seek in the file? */
-		if (sendOff != startoff)
-		{
-			if (lseek(sendFile, (off_t) startoff, SEEK_SET) < 0)
-			{
-				int			err = errno;
-				char		fname[MAXPGPATH];
-
-				XLogFileName(fname, timeline_id, sendSegNo, WalSegSz);
-
-				fatal_error("could not seek in log file %s to offset %u: %s",
-							fname, startoff, strerror(err));
-			}
-			sendOff = startoff;
-		}
-
-		/* How many bytes are within this segment? */
-		if (nbytes > (WalSegSz - startoff))
-			segbytes = WalSegSz - startoff;
-		else
-			segbytes = nbytes;
-
-		readbytes = read(sendFile, p, segbytes);
-		if (readbytes <= 0)
-		{
-			int			err = errno;
-			char		fname[MAXPGPATH];
 			int			save_errno = errno;
 
-			XLogFileName(fname, timeline_id, sendSegNo, WalSegSz);
+			/* File not there yet, try again */
+			pg_usleep(500 * 1000);
+
 			errno = save_errno;
-
-			if (readbytes < 0)
-				fatal_error("could not read from log file %s, offset %u, length %d: %s",
-							fname, sendOff, segbytes, strerror(err));
-			else if (readbytes == 0)
-				fatal_error("could not read from log file %s, offset %u: read %d of %zu",
-							fname, sendOff, readbytes, (Size) segbytes);
+			continue;
 		}
-
-		/* Update state for read */
-		recptr += readbytes;
-
-		sendOff += readbytes;
-		nbytes -= readbytes;
-		p += readbytes;
+		/* Any other error, fall through and fail */
+		break;
 	}
+
+	fatal_error("could not find file \"%s\": %s", fname, strerror(errno));
+	return -1;					/* keep compiler quiet */
 }
 
 /*
  * XLogReader read_page callback
  */
 static int
-XLogDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
-				 XLogRecPtr targetPtr, char *readBuff)
+WALDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
+				XLogRecPtr targetPtr, char *readBuff)
 {
 	XLogDumpPrivate *private = state->private_data;
 	int			count = XLOG_BLCKSZ;
+	WALReadError errinfo;
 
 	if (private->endptr != InvalidXLogRecPtr)
 	{
@@ -425,8 +344,23 @@ XLogDumpReadPage(XLogReaderState *state, XLogRecPtr targetPagePtr, int reqLen,
 		}
 	}
 
-	XLogDumpXLogRead(state->segcxt.ws_dir, private->timeline, targetPagePtr,
-					 readBuff, count);
+	if (!WALRead(readBuff, targetPagePtr, count, private->timeline,
+				 &state->seg, &state->segcxt, WALDumpOpenSegment, &errinfo))
+	{
+		WALOpenSegment *seg = &errinfo.wre_seg;
+		char		fname[MAXPGPATH];
+
+		XLogFileName(fname, seg->ws_tli, seg->ws_segno,
+					 state->segcxt.ws_segsize);
+
+		if (errinfo.wre_errno != 0)
+			fatal_error("could not read in file %s, offset %u, length %zu: %s",
+						fname, errinfo.wre_off, (Size) errinfo.wre_req,
+						strerror(errinfo.wre_errno));
+		else
+			fatal_error("could not read in file %s, offset %u: length: %zu",
+						fname, errinfo.wre_off, (Size) errinfo.wre_req);
+	}
 
 	return count;
 }
@@ -1089,7 +1023,7 @@ main(int argc, char **argv)
 	/* done with argument parsing, do the actual work */
 
 	/* we have everything we need, start reading */
-	xlogreader_state = XLogReaderAllocate(WalSegSz, waldir, XLogDumpReadPage,
+	xlogreader_state = XLogReaderAllocate(WalSegSz, waldir, WALDumpReadPage,
 										  &private);
 	if (!xlogreader_state)
 		fatal_error("out of memory");
diff --git a/src/include/access/xlogreader.h b/src/include/access/xlogreader.h
index 1bbee386e8..0193611b7f 100644
--- a/src/include/access/xlogreader.h
+++ b/src/include/access/xlogreader.h
@@ -36,7 +36,6 @@ typedef struct WALOpenSegment
 {
 	int			ws_file;		/* segment file descriptor */
 	XLogSegNo	ws_segno;		/* segment number */
-	uint32		ws_off;			/* offset in the segment */
 	TimeLineID	ws_tli;			/* timeline ID of the currently open file */
 } WALOpenSegment;
 
@@ -168,6 +167,7 @@ struct XLogReaderState
 	/* last read XLOG position for data currently in readBuf */
 	WALSegmentContext segcxt;
 	WALOpenSegment seg;
+	uint32		segoff;
 
 	/*
 	 * beginning of prior page read, and its TLI.  Doesn't necessarily
@@ -217,6 +217,24 @@ extern XLogReaderState *XLogReaderAllocate(int wal_segment_size,
 /* Free an XLogReader */
 extern void XLogReaderFree(XLogReaderState *state);
 
+/*
+ * Callback to open the specified WAL segment for reading.  Returns a valid
+ * file descriptor when the file was opened successfully.
+ *
+ * "nextSegNo" is the number of the segment to be opened.
+ *
+ * "segcxt" is additional information about the segment.
+ *
+ * "tli_p" is an input/output argument. XLogRead() uses it to pass the
+ * timeline in which the new segment should be found, but the callback can use
+ * it to return the TLI that it actually opened.
+ *
+ * BasicOpenFile() is the preferred way to open the segment file in backend
+ * code, whereas open(2) should be used in frontend.
+ */
+typedef int (*WALSegmentOpen) (XLogSegNo nextSegNo, WALSegmentContext *segcxt,
+							   TimeLineID *tli_p);
+
 /* Initialize supporting structures */
 extern void WALOpenSegmentInit(WALOpenSegment *seg, WALSegmentContext *segcxt,
 							   int segsize, const char *waldir);
@@ -232,6 +250,25 @@ extern bool XLogReaderValidatePageHeader(XLogReaderState *state,
 #ifdef FRONTEND
 extern XLogRecPtr XLogFindNextRecord(XLogReaderState *state, XLogRecPtr RecPtr);
 #endif							/* FRONTEND */
+
+/*
+ * Error information from WALRead that both backend and frontend caller can
+ * process.  Currently only errors from pg_pread can be reported.
+ */
+typedef struct WALReadError
+{
+	int			wre_errno;		/* errno set by the last pg_pread() */
+	int			wre_off;		/* Offset we tried to read from. */
+	int			wre_req;		/* Bytes requested to be read. */
+	int			wre_read;		/* Bytes read by the last read(). */
+	WALOpenSegment wre_seg;		/* Segment we tried to read from. */
+} WALReadError;
+
+extern bool WALRead(char *buf, XLogRecPtr startptr, Size count,
+					TimeLineID tli, WALOpenSegment *seg,
+					WALSegmentContext *segcxt, WALSegmentOpen openSegment,
+					WALReadError *errinfo);
+
 /* Functions for decoding an XLogRecord */
 
 extern bool DecodeXLogRecord(XLogReaderState *state, XLogRecord *record,
diff --git a/src/include/access/xlogutils.h b/src/include/access/xlogutils.h
index 2df98e45b2..0572b24192 100644
--- a/src/include/access/xlogutils.h
+++ b/src/include/access/xlogutils.h
@@ -54,4 +54,6 @@ extern int	read_local_xlog_page(XLogReaderState *state,
 extern void XLogReadDetermineTimeline(XLogReaderState *state,
 									  XLogRecPtr wantPage, uint32 wantLength);
 
+extern void WALReadRaiseError(WALReadError *errinfo);
+
 #endif
-- 
2.20.1


--yrj/dFKFPuw6o+aM--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..97ea882cf71 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index 00b21ede481..c25dbeadff3 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -233,6 +234,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0f6b5df322c..16009fa75a4 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1470,7 +1471,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid		dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index fe6bfeba25e..0d415f5f8f2 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1776,9 +1777,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid		dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin
+		 * is not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..49d1bf4bfac 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+					continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v50 7/8] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--brnevsqjnuzpyok4
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v50-0008-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v51 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--r2slln3zpmilwu22
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v51-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v52 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--gp2pyozrd5pweboh
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v52-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v51 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--r2slln3zpmilwu22
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v51-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v50 7/8] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--brnevsqjnuzpyok4
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v50-0008-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..97ea882cf71 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index 00b21ede481..c25dbeadff3 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -233,6 +234,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0f6b5df322c..16009fa75a4 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1470,7 +1471,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid		dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index fe6bfeba25e..0d415f5f8f2 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1776,9 +1777,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid		dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin
+		 * is not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..49d1bf4bfac 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+					continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..97ea882cf71 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index 00b21ede481..c25dbeadff3 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -233,6 +234,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0f6b5df322c..16009fa75a4 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1470,7 +1471,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid		dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index fe6bfeba25e..0d415f5f8f2 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1776,9 +1777,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid		dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin
+		 * is not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..49d1bf4bfac 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+					continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v50 7/8] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--brnevsqjnuzpyok4
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v50-0008-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v51 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--r2slln3zpmilwu22
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v51-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v52 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--gp2pyozrd5pweboh
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v52-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v50 7/8] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--brnevsqjnuzpyok4
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v50-0008-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..97ea882cf71 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index 00b21ede481..c25dbeadff3 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -233,6 +234,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0f6b5df322c..16009fa75a4 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1470,7 +1471,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid		dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index fe6bfeba25e..0d415f5f8f2 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1776,9 +1777,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid		dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin
+		 * is not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..49d1bf4bfac 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+					continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v51 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--r2slln3zpmilwu22
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v51-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..97ea882cf71 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index 00b21ede481..c25dbeadff3 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -233,6 +234,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0f6b5df322c..16009fa75a4 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1470,7 +1471,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid		dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index fe6bfeba25e..0d415f5f8f2 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1776,9 +1777,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid		dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin
+		 * is not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..49d1bf4bfac 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+					continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v51 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--r2slln3zpmilwu22
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v51-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v50 7/8] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--brnevsqjnuzpyok4
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v50-0008-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..97ea882cf71 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index 00b21ede481..c25dbeadff3 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -233,6 +234,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 0f6b5df322c..16009fa75a4 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1470,7 +1471,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid		dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index fe6bfeba25e..0d415f5f8f2 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1776,9 +1777,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid		dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin
+		 * is not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..49d1bf4bfac 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+					continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v52 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--gp2pyozrd5pweboh
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v52-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v52 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--gp2pyozrd5pweboh
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v52-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v52 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--gp2pyozrd5pweboh
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v52-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v52 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--gp2pyozrd5pweboh
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v52-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v50 7/8] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--brnevsqjnuzpyok4
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v50-0008-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v51 08/10] Introduce an option to make logical replication database specific.
@ 2026-04-03 10:34  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-03 10:34 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch introduces the possibility for a backend to declare that its output
plugin does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in walsender involved in logical replication too, however
that would need thorough analysis of its output plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 ++--
 src/backend/access/index/genam.c            | 18 ++++++++++++++++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 ++
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/commands/repack_worker.c        |  8 +++++++
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/snapbuild.c | 10 ++++++++-
 src/backend/replication/slot.c              | 12 +++++++++--
 src/backend/storage/ipc/procarray.c         | 23 ++++++++++++++++++++-
 src/backend/storage/ipc/standby.c           | 14 +++++++++++--
 src/include/access/genam.h                  |  8 +++++++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 ++-
 src/include/storage/standbydefs.h           |  1 +
 16 files changed, 99 insertions(+), 14 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 2c1c6f88b74..8da8eff93e4 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7336,7 +7336,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index c85166ba849..ff34e246469 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -16,6 +16,7 @@
  */
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/table.h"
 #include "access/xlog_internal.h"
 #include "access/xlogutils.h"
@@ -237,6 +238,13 @@ repack_setup_logical_decoding(Oid relid)
 
 	EnsureLogicalDecodingEnabled();
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	accessSharedCatalogsInDecoding = false;
+
 	/*
 	 * Neither prepare_write nor do_write callback nor update_progress is
 	 * useful for us.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..2e3926e1d13 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -1465,7 +1466,14 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		Oid			dbid;
+
+		/*
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		LogStandbySnapshot(dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..d553bd5dbff 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -39,6 +39,7 @@
 #include <unistd.h>
 #include <sys/stat.h>
 
+#include "access/genam.h"
 #include "access/transam.h"
 #include "access/xlog_internal.h"
 #include "access/xlogrecovery.h"
@@ -1760,9 +1761,16 @@ ReplicationSlotReserveWal(void)
 	if (!RecoveryInProgress() && SlotIsLogical(slot))
 	{
 		XLogRecPtr	flushptr;
+		Oid			dbid;
 
-		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		/*
+		 * Make sure we have enough information to start.
+		 *
+		 * Only consider transactions of the current database if our plugin is
+		 * not supposed to access shared catalogs.
+		 */
+		dbid = accessSharedCatalogsInDecoding ? InvalidOid : MyDatabaseId;
+		flushptr = LogStandbySnapshot(dbid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 755835d63bf..ae19982d88d 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -31,7 +31,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--r2slln3zpmilwu22
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v51-0009-Reserve-replication-slots-specifically-for-REPAC.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v53 1/7] Introduce an option to make logical replication database specific.
@ 2026-04-04 15:16  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-04 15:16 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch adds a new option to logical replication output plugin, to declare
that it does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in the plugin for logical replication too, however that would
need thorough analysis of that plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 +-
 doc/src/sgml/logicaldecoding.sgml           |  4 ++
 src/backend/access/index/genam.c            |  8 +++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 +
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/decode.c    |  8 ++-
 src/backend/replication/logical/logical.c   |  3 ++
 src/backend/replication/logical/snapbuild.c | 59 ++++++++++++++++++---
 src/backend/replication/slot.c              |  2 +-
 src/backend/storage/ipc/procarray.c         | 23 +++++++-
 src/backend/storage/ipc/standby.c           | 14 ++++-
 src/include/access/genam.h                  |  7 +++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/replication/output_plugin.h     |  1 +
 src/include/replication/snapbuild.h         |  3 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 +-
 src/include/storage/standbydefs.h           |  1 +
 20 files changed, 131 insertions(+), 21 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/doc/src/sgml/logicaldecoding.sgml b/doc/src/sgml/logicaldecoding.sgml
index 6dc49108997..28089d1053c 100644
--- a/doc/src/sgml/logicaldecoding.sgml
+++ b/doc/src/sgml/logicaldecoding.sgml
@@ -959,6 +959,7 @@ typedef struct OutputPluginOptions
 {
     OutputPluginOutputType output_type;
     bool        receive_rewrites;
+    bool        need_shared_catalogs;
 } OutputPluginOptions;
 </programlisting>
       <literal>output_type</literal> has to either be set to
@@ -969,6 +970,9 @@ typedef struct OutputPluginOptions
       also be called for changes made by heap rewrites during certain DDL
       operations.  These are of interest to plugins that handle DDL
       replication, but they require special handling.
+      <literal>need_shared_catalogs</literal> can be set to false if you are
+      sure the plugin functions do not access shared system catalogs. It can
+      speed up creation of replication slots that use this plugin.
      </para>
 
      <para>
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..44df2605068 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -394,6 +394,14 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9e8999bbb61..1a6c1456d2c 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7731,7 +7731,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index 57aaef57c61..4299d0bc867 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -381,7 +381,13 @@ standby_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 			{
 				xl_running_xacts *running = (xl_running_xacts *) XLogRecGetData(r);
 
-				SnapBuildProcessRunningXacts(builder, buf->origptr, running);
+
+				/*
+				 * If the plugin does not access shared catalogs, only keep
+				 * track of transactions in the current database.
+				 */
+				SnapBuildProcessRunningXacts(builder, buf->origptr, running,
+											 !ctx->options.need_shared_catalogs);
 
 				/*
 				 * Abort all transactions that we keep track of, that are
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index f20d0c542f3..8ceaf64d164 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -285,6 +285,9 @@ StartupDecodingContext(List *output_plugin_options,
 	ctx->write = do_write;
 	ctx->update_progress = update_progress;
 
+	/* Assume shared catalog access. The startup callback can change it. */
+	ctx->options.need_shared_catalogs = true;
+
 	ctx->output_plugin_options = output_plugin_options;
 
 	ctx->fast_forward = fast_forward;
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..a6738e120c7 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -154,6 +155,14 @@
 static ResourceOwner SavedResourceOwnerDuringExport = NULL;
 static bool ExportInProgress = false;
 
+/*
+ * If a backend is going to do logical decoding and the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 /* ->committed and ->catchange manipulation */
 static void SnapBuildPurgeOlderTxn(SnapBuild *builder);
 
@@ -170,7 +179,8 @@ static inline bool SnapBuildXidHasCatalogChanges(SnapBuild *builder, Transaction
 												 uint32 xinfo);
 
 /* xlog reading helper functions for SnapBuildProcessRunningXacts */
-static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running);
+static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn,
+								  xl_running_xacts *running, bool db_specific);
 static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff);
 
 /* serialization functions */
@@ -1136,7 +1146,8 @@ SnapBuildXidHasCatalogChanges(SnapBuild *builder, TransactionId xid,
  * anymore.
  */
 void
-SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+							 bool db_specific)
 {
 	ReorderBufferTXN *txn;
 	TransactionId xmin;
@@ -1149,7 +1160,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	if (builder->state < SNAPBUILD_CONSISTENT)
 	{
 		/* returns false if there's no point in performing cleanup just yet */
-		if (!SnapBuildFindSnapshot(builder, lsn, running))
+		if (!SnapBuildFindSnapshot(builder, lsn, running, db_specific))
 			return;
 	}
 	else
@@ -1166,8 +1177,14 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * (see SnapBuildCommitTxn).  Because of this, xmax can be lower than
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
+	 *
+	 * If database specific transaction info was used during startup, the info
+	 * for the whole cluster can make xmin go backwards. That would be bad
+	 * because we might no longer have older XIDs in ->committed.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	if (!db_specific ||
+		NormalTransactionIdFollows(running->oldestRunningXid, builder->xmin))
+		builder->xmin = running->oldestRunningXid;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1182,7 +1199,11 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * the record we're reading now.
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
-	if (xmin == InvalidTransactionId)
+
+	/*
+	 * Like above, do not let slot xmin go backwards.
+	 */
+	if (xmin == InvalidTransactionId && !db_specific)
 		xmin = running->oldestRunningXid;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
 		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
@@ -1238,7 +1259,8 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
  * using the xl_running_xacts record.
  */
 static bool
-SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+					  bool db_specific)
 {
 	/* ---
 	 * Build catalog decoding snapshot incrementally using information about
@@ -1265,6 +1287,25 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * ---
 	 */
 
+	if (db_specific)
+	{
+		/*
+		 * If we must only keep track of transactions running in the current
+		 * database, we need transaction info from exactly that database.
+		 */
+		if (running->dbid != MyDatabaseId)
+		{
+			LogStandbySnapshot(MyDatabaseId);
+			return false;
+		}
+
+		/*
+		 * We'd better be able to check during scan if the plugin does not
+		 * lie.
+		 */
+		accessSharedCatalogsInDecoding = false;
+	}
+
 	/*
 	 * xl_running_xacts record is older than what we can use, we might not
 	 * have all necessary catalog rows anymore.
@@ -1465,7 +1506,11 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		/*
+		 * If the last transaction info was about specific database, so needs
+		 * to be the next one - at least until we're in the CONSISTENT state.
+		 */
+		LogStandbySnapshot(running->dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..9533515a63b 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1762,7 +1762,7 @@ ReplicationSlotReserveWal(void)
 		XLogRecPtr	flushptr;
 
 		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		flushptr = LogStandbySnapshot(InvalidOid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..c9a52277be1 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,13 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+
+/*
+ * Keep track of whether logical decoding in this backend promised not to
+ * access shared catalogs, as a safety check.  Somewhat misplaced, but ...
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 10c18d39ff8..13ae3ad4fbb 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -32,7 +32,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/replication/output_plugin.h b/src/include/replication/output_plugin.h
index 842fcde67f9..917f3cff232 100644
--- a/src/include/replication/output_plugin.h
+++ b/src/include/replication/output_plugin.h
@@ -27,6 +27,7 @@ typedef struct OutputPluginOptions
 {
 	OutputPluginOutputType output_type;
 	bool		receive_rewrites;
+	bool		need_shared_catalogs;
 } OutputPluginOptions;
 
 /*
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index a22a83a2f23..d02530a912a 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -92,7 +92,8 @@ extern void SnapBuildProcessNewCid(SnapBuild *builder, TransactionId xid,
 								   XLogRecPtr lsn,
 								   xl_heap_new_cid *xlrec);
 extern void SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn,
-										 xl_running_xacts *running);
+										 xl_running_xacts *running,
+										 bool db_specific);
 extern void SnapBuildSerializationPoint(SnapBuild *builder, XLogRecPtr lsn);
 
 extern bool SnapBuildSnapshotExists(XLogRecPtr lsn);
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--qr3jlalmmcpkiodg
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v53-0002-Fix-a-few-problems-in-index-build-progress-repor.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH] Introduce an option to make logical replication database specific.
@ 2026-04-04 15:16  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-04 15:16 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch adds a new option to logical replication output plugin, to declare
that it does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in the plugin for logical replication too, however that would
need thorough analysis of that plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c         |  4 +-
 doc/src/sgml/logicaldecoding.sgml             |  4 ++
 src/backend/access/index/genam.c              | 18 +++++++
 src/backend/access/rmgrdesc/standbydesc.c     |  2 +
 src/backend/access/transam/xlog.c             |  2 +-
 src/backend/access/transam/xlogfuncs.c        |  2 +-
 src/backend/postmaster/bgwriter.c             |  2 +-
 src/backend/replication/logical/decode.c      |  8 ++-
 src/backend/replication/logical/logical.c     |  5 ++
 src/backend/replication/logical/snapbuild.c   | 52 ++++++++++++++++---
 .../pgoutput_repack/pgoutput_repack.c         |  7 +++
 src/backend/replication/slot.c                |  2 +-
 src/backend/storage/ipc/procarray.c           | 23 +++++++-
 src/backend/storage/ipc/standby.c             | 14 ++++-
 src/include/access/genam.h                    |  8 +++
 src/include/access/xlog_internal.h            |  2 +-
 src/include/replication/output_plugin.h       |  1 +
 src/include/replication/snapbuild.h           |  3 +-
 src/include/storage/procarray.h               |  2 +-
 src/include/storage/standby.h                 |  3 +-
 src/include/storage/standbydefs.h             |  1 +
 21 files changed, 144 insertions(+), 21 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/doc/src/sgml/logicaldecoding.sgml b/doc/src/sgml/logicaldecoding.sgml
index 6dc49108997..28089d1053c 100644
--- a/doc/src/sgml/logicaldecoding.sgml
+++ b/doc/src/sgml/logicaldecoding.sgml
@@ -959,6 +959,7 @@ typedef struct OutputPluginOptions
 {
     OutputPluginOutputType output_type;
     bool        receive_rewrites;
+    bool        need_shared_catalogs;
 } OutputPluginOptions;
 </programlisting>
       <literal>output_type</literal> has to either be set to
@@ -969,6 +970,9 @@ typedef struct OutputPluginOptions
       also be called for changes made by heap rewrites during certain DDL
       operations.  These are of interest to plugins that handle DDL
       replication, but they require special handling.
+      <literal>need_shared_catalogs</literal> can be set to false if you are
+      sure the plugin functions do not access shared system catalogs. It can
+      speed up creation of replication slots that use this plugin.
      </para>
 
      <para>
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9e8999bbb61..1a6c1456d2c 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7731,7 +7731,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index 2be5d8d4bd9..1353d004aac 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -382,7 +382,13 @@ standby_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 			{
 				xl_running_xacts *running = (xl_running_xacts *) XLogRecGetData(r);
 
-				SnapBuildProcessRunningXacts(builder, buf->origptr, running);
+
+				/*
+				 * If the plugin does not access shared catalogs, only keep
+				 * track of transactions in the current database.
+				 */
+				SnapBuildProcessRunningXacts(builder, buf->origptr, running,
+											 !ctx->options.need_shared_catalogs);
 
 				/*
 				 * Abort all transactions that we keep track of, that are
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index f20a0fe70ad..89043a03497 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -289,6 +289,11 @@ StartupDecodingContext(List *output_plugin_options,
 	ctx->write = do_write;
 	ctx->update_progress = update_progress;
 
+	/*
+	 * Assume true for safety, the startup callback can change that.
+	 */
+	ctx->options.need_shared_catalogs = true;
+
 	ctx->output_plugin_options = output_plugin_options;
 
 	ctx->fast_forward = fast_forward;
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..054a7b16f43 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -170,7 +171,8 @@ static inline bool SnapBuildXidHasCatalogChanges(SnapBuild *builder, Transaction
 												 uint32 xinfo);
 
 /* xlog reading helper functions for SnapBuildProcessRunningXacts */
-static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running);
+static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn,
+								  xl_running_xacts *running, bool db_specific);
 static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff);
 
 /* serialization functions */
@@ -1136,7 +1138,8 @@ SnapBuildXidHasCatalogChanges(SnapBuild *builder, TransactionId xid,
  * anymore.
  */
 void
-SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+							 bool db_specific)
 {
 	ReorderBufferTXN *txn;
 	TransactionId xmin;
@@ -1149,7 +1152,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	if (builder->state < SNAPBUILD_CONSISTENT)
 	{
 		/* returns false if there's no point in performing cleanup just yet */
-		if (!SnapBuildFindSnapshot(builder, lsn, running))
+		if (!SnapBuildFindSnapshot(builder, lsn, running, db_specific))
 			return;
 	}
 	else
@@ -1166,8 +1169,13 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * (see SnapBuildCommitTxn).  Because of this, xmax can be lower than
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
+	 *
+	 * If database specific transaction info was used during startup, the info
+	 * for the whole cluster can make xmin go backwards. That would be bad
+	 * because we might no longer have older XIDs in ->committed.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	if (NormalTransactionIdFollows(running->oldestRunningXid, builder->xmin))
+		builder->xmin = running->oldestRunningXid;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1182,7 +1190,10 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * the record we're reading now.
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
-	if (xmin == InvalidTransactionId)
+	/*
+	 * Like above, do not let slot xmin go backwards.
+	 */
+	if (xmin == InvalidTransactionId && !db_specific)
 		xmin = running->oldestRunningXid;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
 		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
@@ -1238,7 +1249,8 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
  * using the xl_running_xacts record.
  */
 static bool
-SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+					  bool db_specific)
 {
 	/* ---
 	 * Build catalog decoding snapshot incrementally using information about
@@ -1265,6 +1277,28 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * ---
 	 */
 
+	if (db_specific)
+	{
+		/*
+		 * If we should only keep track of transactions running in the current
+		 * database, we need transaction info from exactly that
+		 * database. Invalid 'dbid' (all databases) would satisfy our needs
+		 * too, but it could make us wait unnecessarily for completion of
+		 * transactions running in other databases.
+		 */
+		if (running->dbid != MyDatabaseId)
+		{
+			LogStandbySnapshot(MyDatabaseId);
+			return false;
+		}
+
+		/*
+		 * We'd better be able to check during scan if the plugin does not
+		 * lie.
+		 */
+		accessSharedCatalogsInDecoding = false;
+	}
+
 	/*
 	 * xl_running_xacts record is older than what we can use, we might not
 	 * have all necessary catalog rows anymore.
@@ -1465,7 +1499,11 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		/*
+		 * If the last transaction info was about specific database, so needs
+		 * to be the next one - at least until we're in the CONSISTENT state.
+		 */
+		LogStandbySnapshot(running->dbid);
 	}
 }
 
diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
index 221260ca0a8..bb3a880a4c3 100644
--- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c
+++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
@@ -52,6 +52,13 @@ repack_startup(LogicalDecodingContext *ctx, OutputPluginOptions *opt,
 	/* Probably unnecessary, as we don't use the SQL interface ... */
 	opt->output_type = OUTPUT_PLUGIN_BINARY_OUTPUT;
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	opt->need_shared_catalogs = false;
+
 	if (ctx->output_plugin_options != NIL)
 	{
 		ereport(ERROR,
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..9533515a63b 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1762,7 +1762,7 @@ ReplicationSlotReserveWal(void)
 		XLogRecPtr	flushptr;
 
 		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		flushptr = LogStandbySnapshot(InvalidOid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 10c18d39ff8..13ae3ad4fbb 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -32,7 +32,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/replication/output_plugin.h b/src/include/replication/output_plugin.h
index 842fcde67f9..917f3cff232 100644
--- a/src/include/replication/output_plugin.h
+++ b/src/include/replication/output_plugin.h
@@ -27,6 +27,7 @@ typedef struct OutputPluginOptions
 {
 	OutputPluginOutputType output_type;
 	bool		receive_rewrites;
+	bool		need_shared_catalogs;
 } OutputPluginOptions;
 
 /*
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index ccded021433..82552a97997 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -93,7 +93,8 @@ extern void SnapBuildProcessNewCid(SnapBuild *builder, TransactionId xid,
 								   XLogRecPtr lsn,
 								   struct xl_heap_new_cid *xlrec);
 extern void SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn,
-										 struct xl_running_xacts *running);
+										 struct xl_running_xacts *running,
+										 bool db_specific);
 extern void SnapBuildSerializationPoint(SnapBuild *builder, XLogRecPtr lsn);
 
 extern bool SnapBuildSnapshotExists(XLogRecPtr lsn);
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v53 1/7] Introduce an option to make logical replication database specific.
@ 2026-04-04 15:16  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-04 15:16 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch adds a new option to logical replication output plugin, to declare
that it does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in the plugin for logical replication too, however that would
need thorough analysis of that plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 +-
 doc/src/sgml/logicaldecoding.sgml           |  4 ++
 src/backend/access/index/genam.c            |  8 +++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 +
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/decode.c    |  8 ++-
 src/backend/replication/logical/logical.c   |  3 ++
 src/backend/replication/logical/snapbuild.c | 59 ++++++++++++++++++---
 src/backend/replication/slot.c              |  2 +-
 src/backend/storage/ipc/procarray.c         | 23 +++++++-
 src/backend/storage/ipc/standby.c           | 14 ++++-
 src/include/access/genam.h                  |  7 +++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/replication/output_plugin.h     |  1 +
 src/include/replication/snapbuild.h         |  3 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 +-
 src/include/storage/standbydefs.h           |  1 +
 20 files changed, 131 insertions(+), 21 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/doc/src/sgml/logicaldecoding.sgml b/doc/src/sgml/logicaldecoding.sgml
index 6dc49108997..28089d1053c 100644
--- a/doc/src/sgml/logicaldecoding.sgml
+++ b/doc/src/sgml/logicaldecoding.sgml
@@ -959,6 +959,7 @@ typedef struct OutputPluginOptions
 {
     OutputPluginOutputType output_type;
     bool        receive_rewrites;
+    bool        need_shared_catalogs;
 } OutputPluginOptions;
 </programlisting>
       <literal>output_type</literal> has to either be set to
@@ -969,6 +970,9 @@ typedef struct OutputPluginOptions
       also be called for changes made by heap rewrites during certain DDL
       operations.  These are of interest to plugins that handle DDL
       replication, but they require special handling.
+      <literal>need_shared_catalogs</literal> can be set to false if you are
+      sure the plugin functions do not access shared system catalogs. It can
+      speed up creation of replication slots that use this plugin.
      </para>
 
      <para>
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..44df2605068 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -394,6 +394,14 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9e8999bbb61..1a6c1456d2c 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7731,7 +7731,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index 57aaef57c61..4299d0bc867 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -381,7 +381,13 @@ standby_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 			{
 				xl_running_xacts *running = (xl_running_xacts *) XLogRecGetData(r);
 
-				SnapBuildProcessRunningXacts(builder, buf->origptr, running);
+
+				/*
+				 * If the plugin does not access shared catalogs, only keep
+				 * track of transactions in the current database.
+				 */
+				SnapBuildProcessRunningXacts(builder, buf->origptr, running,
+											 !ctx->options.need_shared_catalogs);
 
 				/*
 				 * Abort all transactions that we keep track of, that are
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index f20d0c542f3..8ceaf64d164 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -285,6 +285,9 @@ StartupDecodingContext(List *output_plugin_options,
 	ctx->write = do_write;
 	ctx->update_progress = update_progress;
 
+	/* Assume shared catalog access. The startup callback can change it. */
+	ctx->options.need_shared_catalogs = true;
+
 	ctx->output_plugin_options = output_plugin_options;
 
 	ctx->fast_forward = fast_forward;
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..a6738e120c7 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -154,6 +155,14 @@
 static ResourceOwner SavedResourceOwnerDuringExport = NULL;
 static bool ExportInProgress = false;
 
+/*
+ * If a backend is going to do logical decoding and the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 /* ->committed and ->catchange manipulation */
 static void SnapBuildPurgeOlderTxn(SnapBuild *builder);
 
@@ -170,7 +179,8 @@ static inline bool SnapBuildXidHasCatalogChanges(SnapBuild *builder, Transaction
 												 uint32 xinfo);
 
 /* xlog reading helper functions for SnapBuildProcessRunningXacts */
-static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running);
+static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn,
+								  xl_running_xacts *running, bool db_specific);
 static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff);
 
 /* serialization functions */
@@ -1136,7 +1146,8 @@ SnapBuildXidHasCatalogChanges(SnapBuild *builder, TransactionId xid,
  * anymore.
  */
 void
-SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+							 bool db_specific)
 {
 	ReorderBufferTXN *txn;
 	TransactionId xmin;
@@ -1149,7 +1160,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	if (builder->state < SNAPBUILD_CONSISTENT)
 	{
 		/* returns false if there's no point in performing cleanup just yet */
-		if (!SnapBuildFindSnapshot(builder, lsn, running))
+		if (!SnapBuildFindSnapshot(builder, lsn, running, db_specific))
 			return;
 	}
 	else
@@ -1166,8 +1177,14 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * (see SnapBuildCommitTxn).  Because of this, xmax can be lower than
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
+	 *
+	 * If database specific transaction info was used during startup, the info
+	 * for the whole cluster can make xmin go backwards. That would be bad
+	 * because we might no longer have older XIDs in ->committed.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	if (!db_specific ||
+		NormalTransactionIdFollows(running->oldestRunningXid, builder->xmin))
+		builder->xmin = running->oldestRunningXid;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1182,7 +1199,11 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * the record we're reading now.
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
-	if (xmin == InvalidTransactionId)
+
+	/*
+	 * Like above, do not let slot xmin go backwards.
+	 */
+	if (xmin == InvalidTransactionId && !db_specific)
 		xmin = running->oldestRunningXid;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
 		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
@@ -1238,7 +1259,8 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
  * using the xl_running_xacts record.
  */
 static bool
-SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+					  bool db_specific)
 {
 	/* ---
 	 * Build catalog decoding snapshot incrementally using information about
@@ -1265,6 +1287,25 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * ---
 	 */
 
+	if (db_specific)
+	{
+		/*
+		 * If we must only keep track of transactions running in the current
+		 * database, we need transaction info from exactly that database.
+		 */
+		if (running->dbid != MyDatabaseId)
+		{
+			LogStandbySnapshot(MyDatabaseId);
+			return false;
+		}
+
+		/*
+		 * We'd better be able to check during scan if the plugin does not
+		 * lie.
+		 */
+		accessSharedCatalogsInDecoding = false;
+	}
+
 	/*
 	 * xl_running_xacts record is older than what we can use, we might not
 	 * have all necessary catalog rows anymore.
@@ -1465,7 +1506,11 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		/*
+		 * If the last transaction info was about specific database, so needs
+		 * to be the next one - at least until we're in the CONSISTENT state.
+		 */
+		LogStandbySnapshot(running->dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..9533515a63b 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1762,7 +1762,7 @@ ReplicationSlotReserveWal(void)
 		XLogRecPtr	flushptr;
 
 		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		flushptr = LogStandbySnapshot(InvalidOid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..c9a52277be1 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,13 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+
+/*
+ * Keep track of whether logical decoding in this backend promised not to
+ * access shared catalogs, as a safety check.  Somewhat misplaced, but ...
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 10c18d39ff8..13ae3ad4fbb 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -32,7 +32,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/replication/output_plugin.h b/src/include/replication/output_plugin.h
index 842fcde67f9..917f3cff232 100644
--- a/src/include/replication/output_plugin.h
+++ b/src/include/replication/output_plugin.h
@@ -27,6 +27,7 @@ typedef struct OutputPluginOptions
 {
 	OutputPluginOutputType output_type;
 	bool		receive_rewrites;
+	bool		need_shared_catalogs;
 } OutputPluginOptions;
 
 /*
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index a22a83a2f23..d02530a912a 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -92,7 +92,8 @@ extern void SnapBuildProcessNewCid(SnapBuild *builder, TransactionId xid,
 								   XLogRecPtr lsn,
 								   xl_heap_new_cid *xlrec);
 extern void SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn,
-										 xl_running_xacts *running);
+										 xl_running_xacts *running,
+										 bool db_specific);
 extern void SnapBuildSerializationPoint(SnapBuild *builder, XLogRecPtr lsn);
 
 extern bool SnapBuildSnapshotExists(XLogRecPtr lsn);
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--qr3jlalmmcpkiodg
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v53-0002-Fix-a-few-problems-in-index-build-progress-repor.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v53 1/7] Introduce an option to make logical replication database specific.
@ 2026-04-04 15:16  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-04 15:16 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch adds a new option to logical replication output plugin, to declare
that it does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in the plugin for logical replication too, however that would
need thorough analysis of that plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 +-
 doc/src/sgml/logicaldecoding.sgml           |  4 ++
 src/backend/access/index/genam.c            |  8 +++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 +
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/decode.c    |  8 ++-
 src/backend/replication/logical/logical.c   |  3 ++
 src/backend/replication/logical/snapbuild.c | 59 ++++++++++++++++++---
 src/backend/replication/slot.c              |  2 +-
 src/backend/storage/ipc/procarray.c         | 23 +++++++-
 src/backend/storage/ipc/standby.c           | 14 ++++-
 src/include/access/genam.h                  |  7 +++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/replication/output_plugin.h     |  1 +
 src/include/replication/snapbuild.h         |  3 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 +-
 src/include/storage/standbydefs.h           |  1 +
 20 files changed, 131 insertions(+), 21 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/doc/src/sgml/logicaldecoding.sgml b/doc/src/sgml/logicaldecoding.sgml
index 6dc49108997..28089d1053c 100644
--- a/doc/src/sgml/logicaldecoding.sgml
+++ b/doc/src/sgml/logicaldecoding.sgml
@@ -959,6 +959,7 @@ typedef struct OutputPluginOptions
 {
     OutputPluginOutputType output_type;
     bool        receive_rewrites;
+    bool        need_shared_catalogs;
 } OutputPluginOptions;
 </programlisting>
       <literal>output_type</literal> has to either be set to
@@ -969,6 +970,9 @@ typedef struct OutputPluginOptions
       also be called for changes made by heap rewrites during certain DDL
       operations.  These are of interest to plugins that handle DDL
       replication, but they require special handling.
+      <literal>need_shared_catalogs</literal> can be set to false if you are
+      sure the plugin functions do not access shared system catalogs. It can
+      speed up creation of replication slots that use this plugin.
      </para>
 
      <para>
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..44df2605068 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -394,6 +394,14 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9e8999bbb61..1a6c1456d2c 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7731,7 +7731,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index 57aaef57c61..4299d0bc867 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -381,7 +381,13 @@ standby_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 			{
 				xl_running_xacts *running = (xl_running_xacts *) XLogRecGetData(r);
 
-				SnapBuildProcessRunningXacts(builder, buf->origptr, running);
+
+				/*
+				 * If the plugin does not access shared catalogs, only keep
+				 * track of transactions in the current database.
+				 */
+				SnapBuildProcessRunningXacts(builder, buf->origptr, running,
+											 !ctx->options.need_shared_catalogs);
 
 				/*
 				 * Abort all transactions that we keep track of, that are
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index f20d0c542f3..8ceaf64d164 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -285,6 +285,9 @@ StartupDecodingContext(List *output_plugin_options,
 	ctx->write = do_write;
 	ctx->update_progress = update_progress;
 
+	/* Assume shared catalog access. The startup callback can change it. */
+	ctx->options.need_shared_catalogs = true;
+
 	ctx->output_plugin_options = output_plugin_options;
 
 	ctx->fast_forward = fast_forward;
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..a6738e120c7 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -154,6 +155,14 @@
 static ResourceOwner SavedResourceOwnerDuringExport = NULL;
 static bool ExportInProgress = false;
 
+/*
+ * If a backend is going to do logical decoding and the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 /* ->committed and ->catchange manipulation */
 static void SnapBuildPurgeOlderTxn(SnapBuild *builder);
 
@@ -170,7 +179,8 @@ static inline bool SnapBuildXidHasCatalogChanges(SnapBuild *builder, Transaction
 												 uint32 xinfo);
 
 /* xlog reading helper functions for SnapBuildProcessRunningXacts */
-static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running);
+static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn,
+								  xl_running_xacts *running, bool db_specific);
 static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff);
 
 /* serialization functions */
@@ -1136,7 +1146,8 @@ SnapBuildXidHasCatalogChanges(SnapBuild *builder, TransactionId xid,
  * anymore.
  */
 void
-SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+							 bool db_specific)
 {
 	ReorderBufferTXN *txn;
 	TransactionId xmin;
@@ -1149,7 +1160,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	if (builder->state < SNAPBUILD_CONSISTENT)
 	{
 		/* returns false if there's no point in performing cleanup just yet */
-		if (!SnapBuildFindSnapshot(builder, lsn, running))
+		if (!SnapBuildFindSnapshot(builder, lsn, running, db_specific))
 			return;
 	}
 	else
@@ -1166,8 +1177,14 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * (see SnapBuildCommitTxn).  Because of this, xmax can be lower than
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
+	 *
+	 * If database specific transaction info was used during startup, the info
+	 * for the whole cluster can make xmin go backwards. That would be bad
+	 * because we might no longer have older XIDs in ->committed.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	if (!db_specific ||
+		NormalTransactionIdFollows(running->oldestRunningXid, builder->xmin))
+		builder->xmin = running->oldestRunningXid;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1182,7 +1199,11 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * the record we're reading now.
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
-	if (xmin == InvalidTransactionId)
+
+	/*
+	 * Like above, do not let slot xmin go backwards.
+	 */
+	if (xmin == InvalidTransactionId && !db_specific)
 		xmin = running->oldestRunningXid;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
 		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
@@ -1238,7 +1259,8 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
  * using the xl_running_xacts record.
  */
 static bool
-SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+					  bool db_specific)
 {
 	/* ---
 	 * Build catalog decoding snapshot incrementally using information about
@@ -1265,6 +1287,25 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * ---
 	 */
 
+	if (db_specific)
+	{
+		/*
+		 * If we must only keep track of transactions running in the current
+		 * database, we need transaction info from exactly that database.
+		 */
+		if (running->dbid != MyDatabaseId)
+		{
+			LogStandbySnapshot(MyDatabaseId);
+			return false;
+		}
+
+		/*
+		 * We'd better be able to check during scan if the plugin does not
+		 * lie.
+		 */
+		accessSharedCatalogsInDecoding = false;
+	}
+
 	/*
 	 * xl_running_xacts record is older than what we can use, we might not
 	 * have all necessary catalog rows anymore.
@@ -1465,7 +1506,11 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		/*
+		 * If the last transaction info was about specific database, so needs
+		 * to be the next one - at least until we're in the CONSISTENT state.
+		 */
+		LogStandbySnapshot(running->dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..9533515a63b 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1762,7 +1762,7 @@ ReplicationSlotReserveWal(void)
 		XLogRecPtr	flushptr;
 
 		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		flushptr = LogStandbySnapshot(InvalidOid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..c9a52277be1 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,13 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+
+/*
+ * Keep track of whether logical decoding in this backend promised not to
+ * access shared catalogs, as a safety check.  Somewhat misplaced, but ...
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 10c18d39ff8..13ae3ad4fbb 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -32,7 +32,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/replication/output_plugin.h b/src/include/replication/output_plugin.h
index 842fcde67f9..917f3cff232 100644
--- a/src/include/replication/output_plugin.h
+++ b/src/include/replication/output_plugin.h
@@ -27,6 +27,7 @@ typedef struct OutputPluginOptions
 {
 	OutputPluginOutputType output_type;
 	bool		receive_rewrites;
+	bool		need_shared_catalogs;
 } OutputPluginOptions;
 
 /*
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index a22a83a2f23..d02530a912a 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -92,7 +92,8 @@ extern void SnapBuildProcessNewCid(SnapBuild *builder, TransactionId xid,
 								   XLogRecPtr lsn,
 								   xl_heap_new_cid *xlrec);
 extern void SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn,
-										 xl_running_xacts *running);
+										 xl_running_xacts *running,
+										 bool db_specific);
 extern void SnapBuildSerializationPoint(SnapBuild *builder, XLogRecPtr lsn);
 
 extern bool SnapBuildSnapshotExists(XLogRecPtr lsn);
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--qr3jlalmmcpkiodg
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v53-0002-Fix-a-few-problems-in-index-build-progress-repor.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH] Introduce an option to make logical replication database specific.
@ 2026-04-04 15:16  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-04 15:16 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch adds a new option to logical replication output plugin, to declare
that it does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in the plugin for logical replication too, however that would
need thorough analysis of that plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c         |  4 +-
 doc/src/sgml/logicaldecoding.sgml             |  4 ++
 src/backend/access/index/genam.c              | 18 +++++++
 src/backend/access/rmgrdesc/standbydesc.c     |  2 +
 src/backend/access/transam/xlog.c             |  2 +-
 src/backend/access/transam/xlogfuncs.c        |  2 +-
 src/backend/postmaster/bgwriter.c             |  2 +-
 src/backend/replication/logical/decode.c      |  8 ++-
 src/backend/replication/logical/logical.c     |  5 ++
 src/backend/replication/logical/snapbuild.c   | 52 ++++++++++++++++---
 .../pgoutput_repack/pgoutput_repack.c         |  7 +++
 src/backend/replication/slot.c                |  2 +-
 src/backend/storage/ipc/procarray.c           | 23 +++++++-
 src/backend/storage/ipc/standby.c             | 14 ++++-
 src/include/access/genam.h                    |  8 +++
 src/include/access/xlog_internal.h            |  2 +-
 src/include/replication/output_plugin.h       |  1 +
 src/include/replication/snapbuild.h           |  3 +-
 src/include/storage/procarray.h               |  2 +-
 src/include/storage/standby.h                 |  3 +-
 src/include/storage/standbydefs.h             |  1 +
 21 files changed, 144 insertions(+), 21 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/doc/src/sgml/logicaldecoding.sgml b/doc/src/sgml/logicaldecoding.sgml
index 6dc49108997..28089d1053c 100644
--- a/doc/src/sgml/logicaldecoding.sgml
+++ b/doc/src/sgml/logicaldecoding.sgml
@@ -959,6 +959,7 @@ typedef struct OutputPluginOptions
 {
     OutputPluginOutputType output_type;
     bool        receive_rewrites;
+    bool        need_shared_catalogs;
 } OutputPluginOptions;
 </programlisting>
       <literal>output_type</literal> has to either be set to
@@ -969,6 +970,9 @@ typedef struct OutputPluginOptions
       also be called for changes made by heap rewrites during certain DDL
       operations.  These are of interest to plugins that handle DDL
       replication, but they require special handling.
+      <literal>need_shared_catalogs</literal> can be set to false if you are
+      sure the plugin functions do not access shared system catalogs. It can
+      speed up creation of replication slots that use this plugin.
      </para>
 
      <para>
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9e8999bbb61..1a6c1456d2c 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7731,7 +7731,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index 2be5d8d4bd9..1353d004aac 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -382,7 +382,13 @@ standby_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 			{
 				xl_running_xacts *running = (xl_running_xacts *) XLogRecGetData(r);
 
-				SnapBuildProcessRunningXacts(builder, buf->origptr, running);
+
+				/*
+				 * If the plugin does not access shared catalogs, only keep
+				 * track of transactions in the current database.
+				 */
+				SnapBuildProcessRunningXacts(builder, buf->origptr, running,
+											 !ctx->options.need_shared_catalogs);
 
 				/*
 				 * Abort all transactions that we keep track of, that are
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index f20a0fe70ad..89043a03497 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -289,6 +289,11 @@ StartupDecodingContext(List *output_plugin_options,
 	ctx->write = do_write;
 	ctx->update_progress = update_progress;
 
+	/*
+	 * Assume true for safety, the startup callback can change that.
+	 */
+	ctx->options.need_shared_catalogs = true;
+
 	ctx->output_plugin_options = output_plugin_options;
 
 	ctx->fast_forward = fast_forward;
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..054a7b16f43 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -170,7 +171,8 @@ static inline bool SnapBuildXidHasCatalogChanges(SnapBuild *builder, Transaction
 												 uint32 xinfo);
 
 /* xlog reading helper functions for SnapBuildProcessRunningXacts */
-static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running);
+static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn,
+								  xl_running_xacts *running, bool db_specific);
 static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff);
 
 /* serialization functions */
@@ -1136,7 +1138,8 @@ SnapBuildXidHasCatalogChanges(SnapBuild *builder, TransactionId xid,
  * anymore.
  */
 void
-SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+							 bool db_specific)
 {
 	ReorderBufferTXN *txn;
 	TransactionId xmin;
@@ -1149,7 +1152,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	if (builder->state < SNAPBUILD_CONSISTENT)
 	{
 		/* returns false if there's no point in performing cleanup just yet */
-		if (!SnapBuildFindSnapshot(builder, lsn, running))
+		if (!SnapBuildFindSnapshot(builder, lsn, running, db_specific))
 			return;
 	}
 	else
@@ -1166,8 +1169,13 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * (see SnapBuildCommitTxn).  Because of this, xmax can be lower than
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
+	 *
+	 * If database specific transaction info was used during startup, the info
+	 * for the whole cluster can make xmin go backwards. That would be bad
+	 * because we might no longer have older XIDs in ->committed.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	if (NormalTransactionIdFollows(running->oldestRunningXid, builder->xmin))
+		builder->xmin = running->oldestRunningXid;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1182,7 +1190,10 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * the record we're reading now.
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
-	if (xmin == InvalidTransactionId)
+	/*
+	 * Like above, do not let slot xmin go backwards.
+	 */
+	if (xmin == InvalidTransactionId && !db_specific)
 		xmin = running->oldestRunningXid;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
 		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
@@ -1238,7 +1249,8 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
  * using the xl_running_xacts record.
  */
 static bool
-SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+					  bool db_specific)
 {
 	/* ---
 	 * Build catalog decoding snapshot incrementally using information about
@@ -1265,6 +1277,28 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * ---
 	 */
 
+	if (db_specific)
+	{
+		/*
+		 * If we should only keep track of transactions running in the current
+		 * database, we need transaction info from exactly that
+		 * database. Invalid 'dbid' (all databases) would satisfy our needs
+		 * too, but it could make us wait unnecessarily for completion of
+		 * transactions running in other databases.
+		 */
+		if (running->dbid != MyDatabaseId)
+		{
+			LogStandbySnapshot(MyDatabaseId);
+			return false;
+		}
+
+		/*
+		 * We'd better be able to check during scan if the plugin does not
+		 * lie.
+		 */
+		accessSharedCatalogsInDecoding = false;
+	}
+
 	/*
 	 * xl_running_xacts record is older than what we can use, we might not
 	 * have all necessary catalog rows anymore.
@@ -1465,7 +1499,11 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		/*
+		 * If the last transaction info was about specific database, so needs
+		 * to be the next one - at least until we're in the CONSISTENT state.
+		 */
+		LogStandbySnapshot(running->dbid);
 	}
 }
 
diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
index 221260ca0a8..bb3a880a4c3 100644
--- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c
+++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
@@ -52,6 +52,13 @@ repack_startup(LogicalDecodingContext *ctx, OutputPluginOptions *opt,
 	/* Probably unnecessary, as we don't use the SQL interface ... */
 	opt->output_type = OUTPUT_PLUGIN_BINARY_OUTPUT;
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	opt->need_shared_catalogs = false;
+
 	if (ctx->output_plugin_options != NIL)
 	{
 		ereport(ERROR,
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..9533515a63b 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1762,7 +1762,7 @@ ReplicationSlotReserveWal(void)
 		XLogRecPtr	flushptr;
 
 		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		flushptr = LogStandbySnapshot(InvalidOid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 10c18d39ff8..13ae3ad4fbb 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -32,7 +32,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/replication/output_plugin.h b/src/include/replication/output_plugin.h
index 842fcde67f9..917f3cff232 100644
--- a/src/include/replication/output_plugin.h
+++ b/src/include/replication/output_plugin.h
@@ -27,6 +27,7 @@ typedef struct OutputPluginOptions
 {
 	OutputPluginOutputType output_type;
 	bool		receive_rewrites;
+	bool		need_shared_catalogs;
 } OutputPluginOptions;
 
 /*
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index ccded021433..82552a97997 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -93,7 +93,8 @@ extern void SnapBuildProcessNewCid(SnapBuild *builder, TransactionId xid,
 								   XLogRecPtr lsn,
 								   struct xl_heap_new_cid *xlrec);
 extern void SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn,
-										 struct xl_running_xacts *running);
+										 struct xl_running_xacts *running,
+										 bool db_specific);
 extern void SnapBuildSerializationPoint(SnapBuild *builder, XLogRecPtr lsn);
 
 extern bool SnapBuildSnapshotExists(XLogRecPtr lsn);
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH v53 1/7] Introduce an option to make logical replication database specific.
@ 2026-04-04 15:16  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-04 15:16 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch adds a new option to logical replication output plugin, to declare
that it does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in the plugin for logical replication too, however that would
need thorough analysis of that plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c       |  4 +-
 doc/src/sgml/logicaldecoding.sgml           |  4 ++
 src/backend/access/index/genam.c            |  8 +++
 src/backend/access/rmgrdesc/standbydesc.c   |  2 +
 src/backend/access/transam/xlog.c           |  2 +-
 src/backend/access/transam/xlogfuncs.c      |  2 +-
 src/backend/postmaster/bgwriter.c           |  2 +-
 src/backend/replication/logical/decode.c    |  8 ++-
 src/backend/replication/logical/logical.c   |  3 ++
 src/backend/replication/logical/snapbuild.c | 59 ++++++++++++++++++---
 src/backend/replication/slot.c              |  2 +-
 src/backend/storage/ipc/procarray.c         | 23 +++++++-
 src/backend/storage/ipc/standby.c           | 14 ++++-
 src/include/access/genam.h                  |  7 +++
 src/include/access/xlog_internal.h          |  2 +-
 src/include/replication/output_plugin.h     |  1 +
 src/include/replication/snapbuild.h         |  3 +-
 src/include/storage/procarray.h             |  2 +-
 src/include/storage/standby.h               |  3 +-
 src/include/storage/standbydefs.h           |  1 +
 20 files changed, 131 insertions(+), 21 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/doc/src/sgml/logicaldecoding.sgml b/doc/src/sgml/logicaldecoding.sgml
index 6dc49108997..28089d1053c 100644
--- a/doc/src/sgml/logicaldecoding.sgml
+++ b/doc/src/sgml/logicaldecoding.sgml
@@ -959,6 +959,7 @@ typedef struct OutputPluginOptions
 {
     OutputPluginOutputType output_type;
     bool        receive_rewrites;
+    bool        need_shared_catalogs;
 } OutputPluginOptions;
 </programlisting>
       <literal>output_type</literal> has to either be set to
@@ -969,6 +970,9 @@ typedef struct OutputPluginOptions
       also be called for changes made by heap rewrites during certain DDL
       operations.  These are of interest to plugins that handle DDL
       replication, but they require special handling.
+      <literal>need_shared_catalogs</literal> can be set to false if you are
+      sure the plugin functions do not access shared system catalogs. It can
+      speed up creation of replication slots that use this plugin.
      </para>
 
      <para>
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..44df2605068 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -394,6 +394,14 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9e8999bbb61..1a6c1456d2c 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7731,7 +7731,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index 57aaef57c61..4299d0bc867 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -381,7 +381,13 @@ standby_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 			{
 				xl_running_xacts *running = (xl_running_xacts *) XLogRecGetData(r);
 
-				SnapBuildProcessRunningXacts(builder, buf->origptr, running);
+
+				/*
+				 * If the plugin does not access shared catalogs, only keep
+				 * track of transactions in the current database.
+				 */
+				SnapBuildProcessRunningXacts(builder, buf->origptr, running,
+											 !ctx->options.need_shared_catalogs);
 
 				/*
 				 * Abort all transactions that we keep track of, that are
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index f20d0c542f3..8ceaf64d164 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -285,6 +285,9 @@ StartupDecodingContext(List *output_plugin_options,
 	ctx->write = do_write;
 	ctx->update_progress = update_progress;
 
+	/* Assume shared catalog access. The startup callback can change it. */
+	ctx->options.need_shared_catalogs = true;
+
 	ctx->output_plugin_options = output_plugin_options;
 
 	ctx->fast_forward = fast_forward;
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..a6738e120c7 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -154,6 +155,14 @@
 static ResourceOwner SavedResourceOwnerDuringExport = NULL;
 static bool ExportInProgress = false;
 
+/*
+ * If a backend is going to do logical decoding and the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 /* ->committed and ->catchange manipulation */
 static void SnapBuildPurgeOlderTxn(SnapBuild *builder);
 
@@ -170,7 +179,8 @@ static inline bool SnapBuildXidHasCatalogChanges(SnapBuild *builder, Transaction
 												 uint32 xinfo);
 
 /* xlog reading helper functions for SnapBuildProcessRunningXacts */
-static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running);
+static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn,
+								  xl_running_xacts *running, bool db_specific);
 static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff);
 
 /* serialization functions */
@@ -1136,7 +1146,8 @@ SnapBuildXidHasCatalogChanges(SnapBuild *builder, TransactionId xid,
  * anymore.
  */
 void
-SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+							 bool db_specific)
 {
 	ReorderBufferTXN *txn;
 	TransactionId xmin;
@@ -1149,7 +1160,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	if (builder->state < SNAPBUILD_CONSISTENT)
 	{
 		/* returns false if there's no point in performing cleanup just yet */
-		if (!SnapBuildFindSnapshot(builder, lsn, running))
+		if (!SnapBuildFindSnapshot(builder, lsn, running, db_specific))
 			return;
 	}
 	else
@@ -1166,8 +1177,14 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * (see SnapBuildCommitTxn).  Because of this, xmax can be lower than
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
+	 *
+	 * If database specific transaction info was used during startup, the info
+	 * for the whole cluster can make xmin go backwards. That would be bad
+	 * because we might no longer have older XIDs in ->committed.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	if (!db_specific ||
+		NormalTransactionIdFollows(running->oldestRunningXid, builder->xmin))
+		builder->xmin = running->oldestRunningXid;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1182,7 +1199,11 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * the record we're reading now.
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
-	if (xmin == InvalidTransactionId)
+
+	/*
+	 * Like above, do not let slot xmin go backwards.
+	 */
+	if (xmin == InvalidTransactionId && !db_specific)
 		xmin = running->oldestRunningXid;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
 		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
@@ -1238,7 +1259,8 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
  * using the xl_running_xacts record.
  */
 static bool
-SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+					  bool db_specific)
 {
 	/* ---
 	 * Build catalog decoding snapshot incrementally using information about
@@ -1265,6 +1287,25 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * ---
 	 */
 
+	if (db_specific)
+	{
+		/*
+		 * If we must only keep track of transactions running in the current
+		 * database, we need transaction info from exactly that database.
+		 */
+		if (running->dbid != MyDatabaseId)
+		{
+			LogStandbySnapshot(MyDatabaseId);
+			return false;
+		}
+
+		/*
+		 * We'd better be able to check during scan if the plugin does not
+		 * lie.
+		 */
+		accessSharedCatalogsInDecoding = false;
+	}
+
 	/*
 	 * xl_running_xacts record is older than what we can use, we might not
 	 * have all necessary catalog rows anymore.
@@ -1465,7 +1506,11 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		/*
+		 * If the last transaction info was about specific database, so needs
+		 * to be the next one - at least until we're in the CONSISTENT state.
+		 */
+		LogStandbySnapshot(running->dbid);
 	}
 }
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..9533515a63b 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1762,7 +1762,7 @@ ReplicationSlotReserveWal(void)
 		XLogRecPtr	flushptr;
 
 		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		flushptr = LogStandbySnapshot(InvalidOid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..c9a52277be1 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,13 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+
+/*
+ * Keep track of whether logical decoding in this backend promised not to
+ * access shared catalogs, as a safety check.  Somewhat misplaced, but ...
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 10c18d39ff8..13ae3ad4fbb 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -32,7 +32,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/replication/output_plugin.h b/src/include/replication/output_plugin.h
index 842fcde67f9..917f3cff232 100644
--- a/src/include/replication/output_plugin.h
+++ b/src/include/replication/output_plugin.h
@@ -27,6 +27,7 @@ typedef struct OutputPluginOptions
 {
 	OutputPluginOutputType output_type;
 	bool		receive_rewrites;
+	bool		need_shared_catalogs;
 } OutputPluginOptions;
 
 /*
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index a22a83a2f23..d02530a912a 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -92,7 +92,8 @@ extern void SnapBuildProcessNewCid(SnapBuild *builder, TransactionId xid,
 								   XLogRecPtr lsn,
 								   xl_heap_new_cid *xlrec);
 extern void SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn,
-										 xl_running_xacts *running);
+										 xl_running_xacts *running,
+										 bool db_specific);
 extern void SnapBuildSerializationPoint(SnapBuild *builder, XLogRecPtr lsn);
 
 extern bool SnapBuildSnapshotExists(XLogRecPtr lsn);
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--qr3jlalmmcpkiodg
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v53-0002-Fix-a-few-problems-in-index-build-progress-repor.patch"



^ permalink  raw  reply  [nested|flat] 55+ messages in thread

* [PATCH] Introduce an option to make logical replication database specific.
@ 2026-04-04 15:16  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 55+ messages in thread

From: Antonin Houska @ 2026-04-04 15:16 UTC (permalink / raw)

By default, the logical decoding assumes access to shared catalogs, so the
snapshot builder needs to consider cluster-wide XIDs during startup. That in
turn means that, if any transaction is already running (and has XID assigned),
the snapshot builder needs to wait for its completion, as it does not know if
that transaction performed catalog changes earlier.

Possible problem with this concept is that if REPACK (CONCURRENTLY) is running
in some database, backends running the same command in other databases get
stuck until the first one has committed. Thus only as single backend in the
cluster can run REPACK (CONCURRENTLY) at any time. Likewise, REPACK
(CONCURRENTLY) can block walsenders starting on behalf of subscriptions
throughout the cluster.

This patch adds a new option to logical replication output plugin, to declare
that it does not use shared catalogs (i.e. catalogs that can be changed by
transactions running in other databases in the cluster). In that case, no
snapshot the backend will use during the decoding needs to contain information
about transactions running in other databases. Thus the snapshot builder only
needs to wait for completion of transactions in the current database.

Currently we only use this option in the REPACK background worker. It could
possibly be used in the plugin for logical replication too, however that would
need thorough analysis of that plugin.

The patch bumps WAL version number, due to a new field in xl_running_xacts.
---
 contrib/pg_visibility/pg_visibility.c         |  4 +-
 doc/src/sgml/logicaldecoding.sgml             |  4 ++
 src/backend/access/index/genam.c              | 18 +++++++
 src/backend/access/rmgrdesc/standbydesc.c     |  2 +
 src/backend/access/transam/xlog.c             |  2 +-
 src/backend/access/transam/xlogfuncs.c        |  2 +-
 src/backend/postmaster/bgwriter.c             |  2 +-
 src/backend/replication/logical/decode.c      |  8 ++-
 src/backend/replication/logical/logical.c     |  5 ++
 src/backend/replication/logical/snapbuild.c   | 52 ++++++++++++++++---
 .../pgoutput_repack/pgoutput_repack.c         |  7 +++
 src/backend/replication/slot.c                |  2 +-
 src/backend/storage/ipc/procarray.c           | 23 +++++++-
 src/backend/storage/ipc/standby.c             | 14 ++++-
 src/include/access/genam.h                    |  8 +++
 src/include/access/xlog_internal.h            |  2 +-
 src/include/replication/output_plugin.h       |  1 +
 src/include/replication/snapbuild.h           |  3 +-
 src/include/storage/procarray.h               |  2 +-
 src/include/storage/standby.h                 |  3 +-
 src/include/storage/standbydefs.h             |  1 +
 21 files changed, 144 insertions(+), 21 deletions(-)

diff --git a/contrib/pg_visibility/pg_visibility.c b/contrib/pg_visibility/pg_visibility.c
index dfab0b64cf5..d564bd2a00c 100644
--- a/contrib/pg_visibility/pg_visibility.c
+++ b/contrib/pg_visibility/pg_visibility.c
@@ -621,7 +621,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 	else if (rel == NULL || rel->rd_rel->relisshared)
 	{
 		/* Shared relation: take into account all running xids */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestRunningXid;
@@ -632,7 +632,7 @@ GetStrictOldestNonRemovableTransactionId(Relation rel)
 		 * Normal relation: take into account xids running within the current
 		 * database
 		 */
-		runningTransactions = GetRunningTransactionData();
+		runningTransactions = GetRunningTransactionData(InvalidOid);
 		LWLockRelease(ProcArrayLock);
 		LWLockRelease(XidGenLock);
 		return runningTransactions->oldestDatabaseRunningXid;
diff --git a/doc/src/sgml/logicaldecoding.sgml b/doc/src/sgml/logicaldecoding.sgml
index 6dc49108997..28089d1053c 100644
--- a/doc/src/sgml/logicaldecoding.sgml
+++ b/doc/src/sgml/logicaldecoding.sgml
@@ -959,6 +959,7 @@ typedef struct OutputPluginOptions
 {
     OutputPluginOutputType output_type;
     bool        receive_rewrites;
+    bool        need_shared_catalogs;
 } OutputPluginOptions;
 </programlisting>
       <literal>output_type</literal> has to either be set to
@@ -969,6 +970,9 @@ typedef struct OutputPluginOptions
       also be called for changes made by heap rewrites during certain DDL
       operations.  These are of interest to plugins that handle DDL
       replication, but they require special handling.
+      <literal>need_shared_catalogs</literal> can be set to false if you are
+      sure the plugin functions do not access shared system catalogs. It can
+      speed up creation of replication slots that use this plugin.
      </para>
 
      <para>
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 1408989c568..df092dc999a 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -37,6 +37,14 @@
 #include "utils/ruleutils.h"
 #include "utils/snapmgr.h"
 
+/*
+ * If a backend is going to do logical decoding and if the output plugin does
+ * not need to access shared catalogs, setting this variable to false can make
+ * the decoding startup faster. In particular, the backend will not need to
+ * wait for completion of already running transactions in other databases.
+ */
+bool		accessSharedCatalogsInDecoding = true;
+
 
 /* ----------------------------------------------------------------
  *		general access method routines
@@ -394,6 +402,16 @@ systable_beginscan(Relation heapRelation,
 	SysScanDesc sysscan;
 	Relation	irel;
 
+	/*
+	 * If this backend promised that it won't access shared catalogs during
+	 * logical decoding, this seems to be the right place to check.
+	 *
+	 * XXX Should this be ereport(ERROR) ?
+	 */
+	Assert(!HistoricSnapshotActive() ||
+		   accessSharedCatalogsInDecoding ||
+		   !heapRelation->rd_rel->relisshared);
+
 	if (indexOK &&
 		!IgnoreSystemIndexes &&
 		!ReindexIsProcessingIndex(indexId))
diff --git a/src/backend/access/rmgrdesc/standbydesc.c b/src/backend/access/rmgrdesc/standbydesc.c
index 0a291354ae2..685d1bdb024 100644
--- a/src/backend/access/rmgrdesc/standbydesc.c
+++ b/src/backend/access/rmgrdesc/standbydesc.c
@@ -41,6 +41,8 @@ standby_desc_running_xacts(StringInfo buf, xl_running_xacts *xlrec)
 		for (i = 0; i < xlrec->subxcnt; i++)
 			appendStringInfo(buf, " %u", xlrec->xids[xlrec->xcnt + i]);
 	}
+
+	appendStringInfo(buf, "; dbid: %u", xlrec->dbid);
 }
 
 void
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9e8999bbb61..1a6c1456d2c 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -7731,7 +7731,7 @@ CreateCheckPoint(int flags)
 	 * recovery we don't need to write running xact data.
 	 */
 	if (!shutdown && XLogStandbyInfoActive())
-		LogStandbySnapshot();
+		LogStandbySnapshot(InvalidOid);
 
 	START_CRIT_SECTION();
 
diff --git a/src/backend/access/transam/xlogfuncs.c b/src/backend/access/transam/xlogfuncs.c
index 65bbaeda59c..0f5979691e6 100644
--- a/src/backend/access/transam/xlogfuncs.c
+++ b/src/backend/access/transam/xlogfuncs.c
@@ -245,7 +245,7 @@ pg_log_standby_snapshot(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
 				 errmsg("pg_log_standby_snapshot() can only be used if \"wal_level\" >= \"replica\"")));
 
-	recptr = LogStandbySnapshot();
+	recptr = LogStandbySnapshot(InvalidOid);
 
 	/*
 	 * As a convenience, return the WAL location of the last inserted record
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 1d8947774a9..a30de4262eb 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -289,7 +289,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			if (now >= timeout &&
 				last_snapshot_lsn <= GetLastImportantRecPtr())
 			{
-				last_snapshot_lsn = LogStandbySnapshot();
+				last_snapshot_lsn = LogStandbySnapshot(InvalidOid);
 				last_snapshot_ts = now;
 			}
 		}
diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c
index 2be5d8d4bd9..1353d004aac 100644
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -382,7 +382,13 @@ standby_decode(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 			{
 				xl_running_xacts *running = (xl_running_xacts *) XLogRecGetData(r);
 
-				SnapBuildProcessRunningXacts(builder, buf->origptr, running);
+
+				/*
+				 * If the plugin does not access shared catalogs, only keep
+				 * track of transactions in the current database.
+				 */
+				SnapBuildProcessRunningXacts(builder, buf->origptr, running,
+											 !ctx->options.need_shared_catalogs);
 
 				/*
 				 * Abort all transactions that we keep track of, that are
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index f20a0fe70ad..89043a03497 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -289,6 +289,11 @@ StartupDecodingContext(List *output_plugin_options,
 	ctx->write = do_write;
 	ctx->update_progress = update_progress;
 
+	/*
+	 * Assume true for safety, the startup callback can change that.
+	 */
+	ctx->options.need_shared_catalogs = true;
+
 	ctx->output_plugin_options = output_plugin_options;
 
 	ctx->fast_forward = fast_forward;
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index b4269a3b102..054a7b16f43 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -125,6 +125,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
+#include "access/genam.h"
 #include "access/heapam_xlog.h"
 #include "access/transam.h"
 #include "access/xact.h"
@@ -170,7 +171,8 @@ static inline bool SnapBuildXidHasCatalogChanges(SnapBuild *builder, Transaction
 												 uint32 xinfo);
 
 /* xlog reading helper functions for SnapBuildProcessRunningXacts */
-static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running);
+static bool SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn,
+								  xl_running_xacts *running, bool db_specific);
 static void SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff);
 
 /* serialization functions */
@@ -1136,7 +1138,8 @@ SnapBuildXidHasCatalogChanges(SnapBuild *builder, TransactionId xid,
  * anymore.
  */
 void
-SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+							 bool db_specific)
 {
 	ReorderBufferTXN *txn;
 	TransactionId xmin;
@@ -1149,7 +1152,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	if (builder->state < SNAPBUILD_CONSISTENT)
 	{
 		/* returns false if there's no point in performing cleanup just yet */
-		if (!SnapBuildFindSnapshot(builder, lsn, running))
+		if (!SnapBuildFindSnapshot(builder, lsn, running, db_specific))
 			return;
 	}
 	else
@@ -1166,8 +1169,13 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * (see SnapBuildCommitTxn).  Because of this, xmax can be lower than
 	 * xmin, which looks odd but is correct and actually more efficient, since
 	 * we hit fast paths in heapam_visibility.c.
+	 *
+	 * If database specific transaction info was used during startup, the info
+	 * for the whole cluster can make xmin go backwards. That would be bad
+	 * because we might no longer have older XIDs in ->committed.
 	 */
-	builder->xmin = running->oldestRunningXid;
+	if (NormalTransactionIdFollows(running->oldestRunningXid, builder->xmin))
+		builder->xmin = running->oldestRunningXid;
 
 	/* Remove transactions we don't need to keep track off anymore */
 	SnapBuildPurgeOlderTxn(builder);
@@ -1182,7 +1190,10 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
 	 * the record we're reading now.
 	 */
 	xmin = ReorderBufferGetOldestXmin(builder->reorder);
-	if (xmin == InvalidTransactionId)
+	/*
+	 * Like above, do not let slot xmin go backwards.
+	 */
+	if (xmin == InvalidTransactionId && !db_specific)
 		xmin = running->oldestRunningXid;
 	elog(DEBUG3, "xmin: %u, xmax: %u, oldest running: %u, oldest xmin: %u",
 		 builder->xmin, builder->xmax, running->oldestRunningXid, xmin);
@@ -1238,7 +1249,8 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact
  * using the xl_running_xacts record.
  */
 static bool
-SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running)
+SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *running,
+					  bool db_specific)
 {
 	/* ---
 	 * Build catalog decoding snapshot incrementally using information about
@@ -1265,6 +1277,28 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
 	 * ---
 	 */
 
+	if (db_specific)
+	{
+		/*
+		 * If we should only keep track of transactions running in the current
+		 * database, we need transaction info from exactly that
+		 * database. Invalid 'dbid' (all databases) would satisfy our needs
+		 * too, but it could make us wait unnecessarily for completion of
+		 * transactions running in other databases.
+		 */
+		if (running->dbid != MyDatabaseId)
+		{
+			LogStandbySnapshot(MyDatabaseId);
+			return false;
+		}
+
+		/*
+		 * We'd better be able to check during scan if the plugin does not
+		 * lie.
+		 */
+		accessSharedCatalogsInDecoding = false;
+	}
+
 	/*
 	 * xl_running_xacts record is older than what we can use, we might not
 	 * have all necessary catalog rows anymore.
@@ -1465,7 +1499,11 @@ SnapBuildWaitSnapshot(xl_running_xacts *running, TransactionId cutoff)
 	 */
 	if (!RecoveryInProgress())
 	{
-		LogStandbySnapshot();
+		/*
+		 * If the last transaction info was about specific database, so needs
+		 * to be the next one - at least until we're in the CONSISTENT state.
+		 */
+		LogStandbySnapshot(running->dbid);
 	}
 }
 
diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
index 221260ca0a8..bb3a880a4c3 100644
--- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c
+++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
@@ -52,6 +52,13 @@ repack_startup(LogicalDecodingContext *ctx, OutputPluginOptions *opt,
 	/* Probably unnecessary, as we don't use the SQL interface ... */
 	opt->output_type = OUTPUT_PLUGIN_BINARY_OUTPUT;
 
+	/*
+	 * By declaring that our output plugin does not need shared catalogs, we
+	 * avoid waiting for completion of transactions running in other databases
+	 * than the one we're connected to.
+	 */
+	opt->need_shared_catalogs = false;
+
 	if (ctx->output_plugin_options != NIL)
 	{
 		ereport(ERROR,
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index a9092fc2382..9533515a63b 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1762,7 +1762,7 @@ ReplicationSlotReserveWal(void)
 		XLogRecPtr	flushptr;
 
 		/* make sure we have enough information to start */
-		flushptr = LogStandbySnapshot();
+		flushptr = LogStandbySnapshot(InvalidOid);
 
 		/* and make sure it's fsynced to disk */
 		XLogFlush(flushptr);
diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c
index cc207cb56e3..92ed34128e5 100644
--- a/src/backend/storage/ipc/procarray.c
+++ b/src/backend/storage/ipc/procarray.c
@@ -2631,9 +2631,11 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc)
  *
  * Note that if any transaction has overflowed its cached subtransactions
  * then there is no real need include any subtransactions.
+ *
+ * If 'dbid' is valid, only gather transactions running in that database.
  */
 RunningTransactions
-GetRunningTransactionData(void)
+GetRunningTransactionData(Oid dbid)
 {
 	/* result workspace */
 	static RunningTransactionsData CurrentRunningXactsData;
@@ -2708,6 +2710,18 @@ GetRunningTransactionData(void)
 		if (!TransactionIdIsValid(xid))
 			continue;
 
+		/*
+		 * Filter by database OID if requested.
+		 */
+		if (OidIsValid(dbid))
+		{
+			int			pgprocno = arrayP->pgprocnos[index];
+			PGPROC	   *proc = &allProcs[pgprocno];
+
+			if (proc->databaseId != dbid)
+				continue;
+		}
+
 		/*
 		 * Be careful not to exclude any xids before calculating the values of
 		 * oldestRunningXid and suboverflowed, since these are used to clean
@@ -2758,6 +2772,12 @@ GetRunningTransactionData(void)
 			PGPROC	   *proc = &allProcs[pgprocno];
 			int			nsubxids;
 
+			/*
+			 * Filter by database OID if requested.
+			 */
+			if (OidIsValid(dbid) && proc->databaseId != dbid)
+				continue;
+
 			/*
 			 * Save subtransaction XIDs. Other backends can't add or remove
 			 * entries while we're holding XidGenLock.
@@ -2791,6 +2811,7 @@ GetRunningTransactionData(void)
 	 * increases if slots do.
 	 */
 
+	CurrentRunningXacts->dbid = dbid;
 	CurrentRunningXacts->xcnt = count - subcount;
 	CurrentRunningXacts->subxcnt = subcount;
 	CurrentRunningXacts->subxid_status = suboverflowed ? SUBXIDS_IN_SUBTRANS : SUBXIDS_IN_ARRAY;
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index de9092fdf5b..c653ea742bc 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -1188,6 +1188,14 @@ standby_redo(XLogReaderState *record)
 		xl_running_xacts *xlrec = (xl_running_xacts *) XLogRecGetData(record);
 		RunningTransactionsData running;
 
+		/*
+		 * Records issued for specific database are not suitable for physical
+		 * replication because that affects the whole cluster. In particular,
+		 * the list of XID is probably incomplete here.
+		 */
+		if (OidIsValid(xlrec->dbid))
+			return;
+
 		running.xcnt = xlrec->xcnt;
 		running.subxcnt = xlrec->subxcnt;
 		running.subxid_status = xlrec->subxid_overflow ? SUBXIDS_MISSING : SUBXIDS_IN_ARRAY;
@@ -1277,11 +1285,12 @@ standby_redo(XLogReaderState *record)
  * as there's no independent knob to just enable logical decoding. For
  * details of how this is used, check snapbuild.c's introductory comment.
  *
+ * If 'dbid' is valid, only gather transactions running in that database.
  *
  * Returns the RecPtr of the last inserted record.
  */
 XLogRecPtr
-LogStandbySnapshot(void)
+LogStandbySnapshot(Oid dbid)
 {
 	XLogRecPtr	recptr;
 	RunningTransactions running;
@@ -1314,7 +1323,7 @@ LogStandbySnapshot(void)
 	 * Log details of all in-progress transactions. This should be the last
 	 * record we write, because standby will open up when it sees this.
 	 */
-	running = GetRunningTransactionData();
+	running = GetRunningTransactionData(dbid);
 
 	/*
 	 * GetRunningTransactionData() acquired ProcArrayLock, we must release it.
@@ -1358,6 +1367,7 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
 	xl_running_xacts xlrec;
 	XLogRecPtr	recptr;
 
+	xlrec.dbid = CurrRunningXacts->dbid;
 	xlrec.xcnt = CurrRunningXacts->xcnt;
 	xlrec.subxcnt = CurrRunningXacts->subxcnt;
 	xlrec.subxid_overflow = (CurrRunningXacts->subxid_status != SUBXIDS_IN_ARRAY);
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index b69320a7fc8..56c573399ab 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -136,6 +136,14 @@ typedef struct IndexOrderByDistance
 	bool		isnull;
 } IndexOrderByDistance;
 
+/*
+ * Is the backend interested in shared catalogs when performing logical
+ * decoding?
+ *
+ * XXX Is there a better place for this declaration?
+ */
+extern bool accessSharedCatalogsInDecoding;
+
 /*
  * generalized index_ interface routines (in indexam.c)
  */
diff --git a/src/include/access/xlog_internal.h b/src/include/access/xlog_internal.h
index 10c18d39ff8..13ae3ad4fbb 100644
--- a/src/include/access/xlog_internal.h
+++ b/src/include/access/xlog_internal.h
@@ -32,7 +32,7 @@
 /*
  * Each page of XLOG file has a header like this:
  */
-#define XLOG_PAGE_MAGIC 0xD11E	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD11F	/* can be used as WAL version indicator */
 
 typedef struct XLogPageHeaderData
 {
diff --git a/src/include/replication/output_plugin.h b/src/include/replication/output_plugin.h
index 842fcde67f9..917f3cff232 100644
--- a/src/include/replication/output_plugin.h
+++ b/src/include/replication/output_plugin.h
@@ -27,6 +27,7 @@ typedef struct OutputPluginOptions
 {
 	OutputPluginOutputType output_type;
 	bool		receive_rewrites;
+	bool		need_shared_catalogs;
 } OutputPluginOptions;
 
 /*
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index ccded021433..82552a97997 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -93,7 +93,8 @@ extern void SnapBuildProcessNewCid(SnapBuild *builder, TransactionId xid,
 								   XLogRecPtr lsn,
 								   struct xl_heap_new_cid *xlrec);
 extern void SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn,
-										 struct xl_running_xacts *running);
+										 struct xl_running_xacts *running,
+										 bool db_specific);
 extern void SnapBuildSerializationPoint(SnapBuild *builder, XLogRecPtr lsn);
 
 extern bool SnapBuildSnapshotExists(XLogRecPtr lsn);
diff --git a/src/include/storage/procarray.h b/src/include/storage/procarray.h
index abdf021e66e..377b3060b9f 100644
--- a/src/include/storage/procarray.h
+++ b/src/include/storage/procarray.h
@@ -49,7 +49,7 @@ extern bool ProcArrayInstallImportedXmin(TransactionId xmin,
 										 VirtualTransactionId *sourcevxid);
 extern bool ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc);
 
-extern RunningTransactions GetRunningTransactionData(void);
+extern RunningTransactions GetRunningTransactionData(Oid dbid);
 
 extern bool TransactionIdIsInProgress(TransactionId xid);
 extern TransactionId GetOldestNonRemovableTransactionId(Relation rel);
diff --git a/src/include/storage/standby.h b/src/include/storage/standby.h
index 6a314c693cd..8715c08e94f 100644
--- a/src/include/storage/standby.h
+++ b/src/include/storage/standby.h
@@ -126,6 +126,7 @@ typedef enum
 
 typedef struct RunningTransactionsData
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	subxids_array_status subxid_status;
@@ -143,7 +144,7 @@ typedef RunningTransactionsData *RunningTransactions;
 extern void LogAccessExclusiveLock(Oid dbOid, Oid relOid);
 extern void LogAccessExclusiveLockPrepare(void);
 
-extern XLogRecPtr LogStandbySnapshot(void);
+extern XLogRecPtr LogStandbySnapshot(Oid dbid);
 extern void LogStandbyInvalidations(int nmsgs, SharedInvalidationMessage *msgs,
 									bool relcacheInitFileInval);
 
diff --git a/src/include/storage/standbydefs.h b/src/include/storage/standbydefs.h
index 231d251fd51..e75b7078766 100644
--- a/src/include/storage/standbydefs.h
+++ b/src/include/storage/standbydefs.h
@@ -46,6 +46,7 @@ typedef struct xl_standby_locks
  */
 typedef struct xl_running_xacts
 {
+	Oid			dbid;			/* only track xacts in this database */
 	int			xcnt;			/* # of xact ids in xids[] */
 	int			subxcnt;		/* # of subxact ids in xids[] */
 	bool		subxid_overflow;	/* snapshot overflowed, subxids missing */
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 55+ messages in thread