Introduce replication progress tracking infrastructure.

When implementing a replication solution ontop of logical decoding, two related problems exist: * How to safely keep track of replication progress * How to change replication behavior, based on the origin of a row; e.g. to avoid loops in bi-directional replication setups The solution to these problems, as implemented here, consist out of three parts: 1) 'replication origins', which identify nodes in a replication setup. 2) 'replication progress tracking', which remembers, for each replication origin, how far replay has progressed in a efficient and crash safe manner. 3) The ability to filter out changes performed on the behest of a replication origin during logical decoding; this allows complex replication topologies. E.g. by filtering all replayed changes out. Most of this could also be implemented in "userspace", e.g. by inserting additional rows contain origin information, but that ends up being much less efficient and more complicated. We don't want to require various replication solutions to reimplement logic for this independently. The infrastructure is intended to be generic enough to be reusable. This infrastructure also replaces the 'nodeid' infrastructure of commit timestamps. It is intended to provide all the former capabilities, except that there's only 2^16 different origins; but now they integrate with logical decoding. Additionally more functionality is accessible via SQL. Since the commit timestamp infrastructure has also been introduced in 9.5 (commit 73c986add) changing the API is not a problem. For now the number of origins for which the replication progress can be tracked simultaneously is determined by the max_replication_slots GUC. That GUC is not a perfect match to configure this, but there doesn't seem to be sufficient reason to introduce a separate new one. Bumps both catversion and wal page magic. Author: Andres Freund, with contributions from Petr Jelinek and Craig Ringer Reviewed-By: Heikki Linnakangas, Petr Jelinek, Robert Haas, Steve Singer Discussion: 20150216002155.GI15326@awork2.anarazel.de, 20140923182422.GA15776@alap3.anarazel.de, 20131114172632.GE7522@alap2.anarazel.de
2025-10-19 15:49:24 +03:00 · 2015-04-29 19:30:53 +02:00
parent c6e96a2f98
commit 5aa2350426
52 changed files with 2766 additions and 89 deletions
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -2189,6 +2189,9 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 							(char *) heaptup->t_data + SizeofHeapTupleHeader,
 							heaptup->t_len - SizeofHeapTupleHeader);

+		/* filtering by origin on a row level is much more efficient */
+		XLogIncludeOrigin();
+
 		recptr = XLogInsert(RM_HEAP_ID, info);

 		PageSetLSN(page, recptr);
@@ -2499,6 +2502,10 @@ heap_multi_insert(Relation relation, HeapTuple *tuples, int ntuples,
 			XLogRegisterBuffer(0, buffer, REGBUF_STANDARD | bufflags);

 			XLogRegisterBufData(0, tupledata, totaldatalen);
+
+			/* filtering by origin on a row level is much more efficient */
+			XLogIncludeOrigin();
+
 			recptr = XLogInsert(RM_HEAP2_ID, info);

 			PageSetLSN(page, recptr);
@@ -2920,6 +2927,9 @@ l1:
 							 - SizeofHeapTupleHeader);
 		}

+		/* filtering by origin on a row level is much more efficient */
+		XLogIncludeOrigin();
+
 		recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE);

 		PageSetLSN(page, recptr);
@@ -4650,6 +4660,8 @@ failed:
 											  tuple->t_data->t_infomask2);
 		XLogRegisterData((char *) &xlrec, SizeOfHeapLock);

+		/* we don't decode row locks atm, so no need to log the origin */
+
 		recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_LOCK);

 		PageSetLSN(page, recptr);
@@ -5429,6 +5441,8 @@ heap_inplace_update(Relation relation, HeapTuple tuple)
 		XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
 		XLogRegisterBufData(0, (char *) htup + htup->t_hoff, newlen);

+		/* inplace updates aren't decoded atm, don't log the origin */
+
 		recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_INPLACE);

 		PageSetLSN(page, recptr);
@@ -6787,6 +6801,9 @@ log_heap_update(Relation reln, Buffer oldbuf,
 						 old_key_tuple->t_len - SizeofHeapTupleHeader);
 	}

+	/* filtering by origin on a row level is much more efficient */
+	XLogIncludeOrigin();
+
 	recptr = XLogInsert(RM_HEAP_ID, info);

 	return recptr;
@@ -6860,6 +6877,8 @@ log_heap_new_cid(Relation relation, HeapTuple tup)
 	XLogBeginInsert();
 	XLogRegisterData((char *) &xlrec, SizeOfHeapNewCid);

+	/* will be looked at irrespective of origin */
+
 	recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_NEW_CID);

 	return recptr;
--- a/src/backend/access/rmgrdesc/Makefile
+++ b/src/backend/access/rmgrdesc/Makefile
@@ -9,8 +9,8 @@ top_builddir = ../../../..
 include $(top_builddir)/src/Makefile.global

 OBJS = brindesc.o clogdesc.o committsdesc.o dbasedesc.o gindesc.o gistdesc.o \
-	   hashdesc.o heapdesc.o \
-	   mxactdesc.o nbtdesc.o relmapdesc.o seqdesc.o smgrdesc.o spgdesc.o \
+	   hashdesc.o heapdesc.o mxactdesc.o nbtdesc.o relmapdesc.o \
+	   replorigindesc.o seqdesc.o smgrdesc.o spgdesc.o \
 	   standbydesc.o tblspcdesc.o xactdesc.o xlogdesc.o

 include $(top_srcdir)/src/backend/common.mk
--- a/src/backend/access/rmgrdesc/replorigindesc.c
+++ b/src/backend/access/rmgrdesc/replorigindesc.c
@@ -0,0 +1,61 @@
+/*-------------------------------------------------------------------------
+ *
+ * replorigindesc.c
+ *    rmgr descriptor routines for replication/logical/replication_origin.c
+ *
+ * Portions Copyright (c) 2015, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ *    src/backend/access/rmgrdesc/replorigindesc.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "replication/origin.h"
+
+void
+replorigin_desc(StringInfo buf, XLogReaderState *record)
+{
+	char	   *rec = XLogRecGetData(record);
+	uint8		info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;
+
+	switch (info)
+	{
+		case XLOG_REPLORIGIN_SET:
+			{
+				xl_replorigin_set *xlrec;
+				xlrec = (xl_replorigin_set *) rec;
+
+				appendStringInfo(buf, "set %u; lsn %X/%X; force: %d",
+								 xlrec->node_id,
+								 (uint32) (xlrec->remote_lsn >> 32),
+								 (uint32) xlrec->remote_lsn,
+								 xlrec->force);
+				break;
+			}
+		case XLOG_REPLORIGIN_DROP:
+			{
+				xl_replorigin_drop *xlrec;
+				xlrec = (xl_replorigin_drop *) rec;
+
+				appendStringInfo(buf, "drop %u", xlrec->node_id);
+				break;
+			}
+	}
+}
+
+const char *
+replorigin_identify(uint8 info)
+{
+	switch (info)
+	{
+		case XLOG_REPLORIGIN_SET:
+			return "SET";
+		case XLOG_REPLORIGIN_DROP:
+			return "DROP";
+		default:
+			return NULL;
+	}
+}
--- a/src/backend/access/rmgrdesc/xactdesc.c
+++ b/src/backend/access/rmgrdesc/xactdesc.c
@@ -101,6 +101,16 @@ ParseCommitRecord(uint8 info, xl_xact_commit *xlrec, xl_xact_parsed_commit *pars

 		data += sizeof(xl_xact_twophase);
 	}
+
+	if (parsed->xinfo & XACT_XINFO_HAS_ORIGIN)
+	{
+		xl_xact_origin *xl_origin = (xl_xact_origin *) data;
+
+		parsed->origin_lsn = xl_origin->origin_lsn;
+		parsed->origin_timestamp = xl_origin->origin_timestamp;
+
+		data += sizeof(xl_xact_origin);
+	}
 }

 void
@@ -156,7 +166,7 @@ ParseAbortRecord(uint8 info, xl_xact_abort *xlrec, xl_xact_parsed_abort *parsed)
 }

 static void
-xact_desc_commit(StringInfo buf, uint8 info, xl_xact_commit *xlrec)
+xact_desc_commit(StringInfo buf, uint8 info, xl_xact_commit *xlrec, RepOriginId origin_id)
 {
 	xl_xact_parsed_commit parsed;
 	int			i;
@@ -218,6 +228,15 @@ xact_desc_commit(StringInfo buf, uint8 info, xl_xact_commit *xlrec)

 	if (XactCompletionForceSyncCommit(parsed.xinfo))
 		appendStringInfo(buf, "; sync");
+
+	if (parsed.xinfo & XACT_XINFO_HAS_ORIGIN)
+	{
+		appendStringInfo(buf, "; origin: node %u, lsn %X/%X, at %s",
+						 origin_id,
+						 (uint32)(parsed.origin_lsn >> 32),
+						 (uint32)parsed.origin_lsn,
+						 timestamptz_to_str(parsed.origin_timestamp));
+	}
 }

 static void
@@ -274,7 +293,8 @@ xact_desc(StringInfo buf, XLogReaderState *record)
 	{
 		xl_xact_commit *xlrec = (xl_xact_commit *) rec;

-		xact_desc_commit(buf, XLogRecGetInfo(record), xlrec);
+		xact_desc_commit(buf, XLogRecGetInfo(record), xlrec,
+						 XLogRecGetOrigin(record));
 	}
 	else if (info == XLOG_XACT_ABORT || info == XLOG_XACT_ABORT_PREPARED)
 	{
--- a/src/backend/access/transam/commit_ts.c
+++ b/src/backend/access/transam/commit_ts.c
@@ -49,18 +49,18 @@
 */

 /*
- * We need 8+4 bytes per xact.  Note that enlarging this struct might mean
+ * We need 8+2 bytes per xact.  Note that enlarging this struct might mean
 * the largest possible file name is more than 5 chars long; see
 * SlruScanDirectory.
 */
 typedef struct CommitTimestampEntry
 {
 	TimestampTz		time;
-	CommitTsNodeId	nodeid;
+	RepOriginId		nodeid;
 } CommitTimestampEntry;

 #define SizeOfCommitTimestampEntry (offsetof(CommitTimestampEntry, nodeid) + \
-									sizeof(CommitTsNodeId))
+									sizeof(RepOriginId))

 #define COMMIT_TS_XACTS_PER_PAGE \
 	(BLCKSZ / SizeOfCommitTimestampEntry)
@@ -93,43 +93,18 @@ CommitTimestampShared	*commitTsShared;
 /* GUC variable */
 bool	track_commit_timestamp;

-static CommitTsNodeId default_node_id = InvalidCommitTsNodeId;
-
 static void SetXidCommitTsInPage(TransactionId xid, int nsubxids,
 					 TransactionId *subxids, TimestampTz ts,
-					 CommitTsNodeId nodeid, int pageno);
+					 RepOriginId nodeid, int pageno);
 static void TransactionIdSetCommitTs(TransactionId xid, TimestampTz ts,
-						  CommitTsNodeId nodeid, int slotno);
+						  RepOriginId nodeid, int slotno);
 static int	ZeroCommitTsPage(int pageno, bool writeXlog);
 static bool CommitTsPagePrecedes(int page1, int page2);
 static void WriteZeroPageXlogRec(int pageno);
 static void WriteTruncateXlogRec(int pageno);
 static void WriteSetTimestampXlogRec(TransactionId mainxid, int nsubxids,
 						 TransactionId *subxids, TimestampTz timestamp,
-						 CommitTsNodeId nodeid);
-
-
-/*
- * CommitTsSetDefaultNodeId
- *
- * Set default nodeid for current backend.
- */
-void
-CommitTsSetDefaultNodeId(CommitTsNodeId nodeid)
-{
-	default_node_id = nodeid;
-}
-
-/*
- * CommitTsGetDefaultNodeId
- *
- * Set default nodeid for current backend.
- */
-CommitTsNodeId
-CommitTsGetDefaultNodeId(void)
-{
-	return default_node_id;
-}
+						 RepOriginId nodeid);

 /*
 * TransactionTreeSetCommitTsData
@@ -156,7 +131,7 @@ CommitTsGetDefaultNodeId(void)
 void
 TransactionTreeSetCommitTsData(TransactionId xid, int nsubxids,
 							   TransactionId *subxids, TimestampTz timestamp,
-							   CommitTsNodeId nodeid, bool do_xlog)
+							   RepOriginId nodeid, bool do_xlog)
 {
 	int			i;
 	TransactionId headxid;
@@ -234,7 +209,7 @@ TransactionTreeSetCommitTsData(TransactionId xid, int nsubxids,
 static void
 SetXidCommitTsInPage(TransactionId xid, int nsubxids,
 					 TransactionId *subxids, TimestampTz ts,
-					 CommitTsNodeId nodeid, int pageno)
+					 RepOriginId nodeid, int pageno)
 {
 	int			slotno;
 	int			i;
@@ -259,7 +234,7 @@ SetXidCommitTsInPage(TransactionId xid, int nsubxids,
 */
 static void
 TransactionIdSetCommitTs(TransactionId xid, TimestampTz ts,
-						 CommitTsNodeId nodeid, int slotno)
+						 RepOriginId nodeid, int slotno)
 {
 	int			entryno = TransactionIdToCTsEntry(xid);
 	CommitTimestampEntry entry;
@@ -282,7 +257,7 @@ TransactionIdSetCommitTs(TransactionId xid, TimestampTz ts,
 */
 bool
 TransactionIdGetCommitTsData(TransactionId xid, TimestampTz *ts,
-							 CommitTsNodeId *nodeid)
+							 RepOriginId *nodeid)
 {
 	int			pageno = TransactionIdToCTsPage(xid);
 	int			entryno = TransactionIdToCTsEntry(xid);
@@ -322,7 +297,7 @@ TransactionIdGetCommitTsData(TransactionId xid, TimestampTz *ts,
 		if (ts)
 			*ts = 0;
 		if (nodeid)
-			*nodeid = InvalidCommitTsNodeId;
+			*nodeid = InvalidRepOriginId;
 		return false;
 	}

@@ -373,7 +348,7 @@ TransactionIdGetCommitTsData(TransactionId xid, TimestampTz *ts,
 * as NULL if not wanted.
 */
 TransactionId
-GetLatestCommitTsData(TimestampTz *ts, CommitTsNodeId *nodeid)
+GetLatestCommitTsData(TimestampTz *ts, RepOriginId *nodeid)
 {
 	TransactionId	xid;

@@ -503,7 +478,7 @@ CommitTsShmemInit(void)

 		commitTsShared->xidLastCommit = InvalidTransactionId;
 		TIMESTAMP_NOBEGIN(commitTsShared->dataLastCommit.time);
-		commitTsShared->dataLastCommit.nodeid = InvalidCommitTsNodeId;
+		commitTsShared->dataLastCommit.nodeid = InvalidRepOriginId;
 	}
 	else
 		Assert(found);
@@ -857,7 +832,7 @@ WriteTruncateXlogRec(int pageno)
 static void
 WriteSetTimestampXlogRec(TransactionId mainxid, int nsubxids,
 						 TransactionId *subxids, TimestampTz timestamp,
-						 CommitTsNodeId nodeid)
+						 RepOriginId nodeid)
 {
 	xl_commit_ts_set	record;

--- a/src/backend/access/transam/rmgr.c
+++ b/src/backend/access/transam/rmgr.c
@@ -23,6 +23,7 @@
 #include "commands/dbcommands_xlog.h"
 #include "commands/sequence.h"
 #include "commands/tablespace.h"
+#include "replication/origin.h"
 #include "storage/standby.h"
 #include "utils/relmapper.h"

--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -40,8 +40,10 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
+#include "replication/logical.h"
 #include "replication/walsender.h"
 #include "replication/syncrep.h"
+#include "replication/origin.h"
 #include "storage/fd.h"
 #include "storage/lmgr.h"
 #include "storage/predicate.h"
@@ -1073,21 +1075,27 @@ RecordTransactionCommit(void)
 							nmsgs, invalMessages,
 							RelcacheInitFileInval, forceSyncCommit,
 							InvalidTransactionId /* plain commit */);
-	}

-	/*
-	 * We only need to log the commit timestamp separately if the node
-	 * identifier is a valid value; the commit record above already contains
-	 * the timestamp info otherwise, and will be used to load it.
-	 */
-	if (markXidCommitted)
-	{
-		CommitTsNodeId		node_id;
+		/*
+		 * Record plain commit ts if not replaying remote actions, or if no
+		 * timestamp is configured.
+		 */
+		if (replorigin_sesssion_origin == InvalidRepOriginId ||
+			replorigin_sesssion_origin == DoNotReplicateId ||
+			replorigin_sesssion_origin_timestamp == 0)
+			replorigin_sesssion_origin_timestamp = xactStopTimestamp;
+		else
+			replorigin_session_advance(replorigin_sesssion_origin_lsn,
+									   XactLastRecEnd);

-		node_id = CommitTsGetDefaultNodeId();
+		/*
+		 * We don't need to WAL log origin or timestamp here, the commit
+		 * record contains all the necessary information and will redo the SET
+		 * action during replay.
+		 */
 		TransactionTreeSetCommitTsData(xid, nchildren, children,
-									   xactStopTimestamp,
-									   node_id, node_id != InvalidCommitTsNodeId);
+									   replorigin_sesssion_origin_timestamp,
+									   replorigin_sesssion_origin, false);
 	}

 	/*
@@ -1176,9 +1184,11 @@ RecordTransactionCommit(void)
 	if (wrote_xlog && markXidCommitted)
 		SyncRepWaitForLSN(XactLastRecEnd);

+	/* remember end of last commit record */
+	XactLastCommitEnd = XactLastRecEnd;
+
 	/* Reset XactLastRecEnd until the next transaction writes something */
 	XactLastRecEnd = 0;
-
 cleanup:
 	/* Clean up local data */
 	if (rels)
@@ -4611,6 +4621,7 @@ XactLogCommitRecord(TimestampTz commit_time,
 	xl_xact_relfilenodes xl_relfilenodes;
 	xl_xact_invals		xl_invals;
 	xl_xact_twophase	xl_twophase;
+	xl_xact_origin		xl_origin;

 	uint8				info;

@@ -4668,6 +4679,15 @@ XactLogCommitRecord(TimestampTz commit_time,
 		xl_twophase.xid = twophase_xid;
 	}

+	/* dump transaction origin information */
+	if (replorigin_sesssion_origin != InvalidRepOriginId)
+	{
+		xl_xinfo.xinfo |= XACT_XINFO_HAS_ORIGIN;
+
+		xl_origin.origin_lsn = replorigin_sesssion_origin_lsn;
+		xl_origin.origin_timestamp = replorigin_sesssion_origin_timestamp;
+	}
+
 	if (xl_xinfo.xinfo != 0)
 		info |= XLOG_XACT_HAS_INFO;

@@ -4709,6 +4729,12 @@ XactLogCommitRecord(TimestampTz commit_time,
 	if (xl_xinfo.xinfo & XACT_XINFO_HAS_TWOPHASE)
 		XLogRegisterData((char *) (&xl_twophase), sizeof(xl_xact_twophase));

+	if (xl_xinfo.xinfo & XACT_XINFO_HAS_ORIGIN)
+		XLogRegisterData((char *) (&xl_origin), sizeof(xl_xact_origin));
+
+	/* we allow filtering by xacts */
+	XLogIncludeOrigin();
+
 	return XLogInsert(RM_XACT_ID, info);
 }

@@ -4806,10 +4832,12 @@ XactLogAbortRecord(TimestampTz abort_time,
 static void
 xact_redo_commit(xl_xact_parsed_commit *parsed,
 				 TransactionId xid,
-				 XLogRecPtr lsn)
+				 XLogRecPtr lsn,
+				 RepOriginId origin_id)
 {
 	TransactionId max_xid;
 	int			i;
+	TimestampTz	commit_time;

 	max_xid = TransactionIdLatest(xid, parsed->nsubxacts, parsed->subxacts);

@@ -4829,9 +4857,16 @@ xact_redo_commit(xl_xact_parsed_commit *parsed,
 		LWLockRelease(XidGenLock);
 	}

+	Assert(!!(parsed->xinfo & XACT_XINFO_HAS_ORIGIN) == (origin_id != InvalidRepOriginId));
+
+	if (parsed->xinfo & XACT_XINFO_HAS_ORIGIN)
+		commit_time = parsed->origin_timestamp;
+	else
+		commit_time = parsed->xact_time;
+
 	/* Set the transaction commit timestamp and metadata */
 	TransactionTreeSetCommitTsData(xid, parsed->nsubxacts, parsed->subxacts,
-								   parsed->xact_time, InvalidCommitTsNodeId,
+								   commit_time, origin_id,
 								   false);

 	if (standbyState == STANDBY_DISABLED)
@@ -4892,6 +4927,13 @@ xact_redo_commit(xl_xact_parsed_commit *parsed,
 		StandbyReleaseLockTree(xid, 0, NULL);
 	}

+	if (parsed->xinfo & XACT_XINFO_HAS_ORIGIN)
+	{
+		/* recover apply progress */
+		replorigin_advance(origin_id, parsed->origin_lsn, lsn,
+						   false /* backward */, false /* WAL */);
+	}
+
 	/* Make sure files supposed to be dropped are dropped */
 	if (parsed->nrels > 0)
 	{
@@ -5047,13 +5089,13 @@ xact_redo(XLogReaderState *record)
 		{
 			Assert(!TransactionIdIsValid(parsed.twophase_xid));
 			xact_redo_commit(&parsed, XLogRecGetXid(record),
-							 record->EndRecPtr);
+							 record->EndRecPtr, XLogRecGetOrigin(record));
 		}
 		else
 		{
 			Assert(TransactionIdIsValid(parsed.twophase_xid));
 			xact_redo_commit(&parsed, parsed.twophase_xid,
-							 record->EndRecPtr);
+							 record->EndRecPtr, XLogRecGetOrigin(record));
 			RemoveTwoPhaseFile(parsed.twophase_xid, false);
 		}
 	}
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -44,6 +44,7 @@
 #include "postmaster/startup.h"
 #include "replication/logical.h"
 #include "replication/slot.h"
+#include "replication/origin.h"
 #include "replication/snapbuild.h"
 #include "replication/walreceiver.h"
 #include "replication/walsender.h"
@@ -295,6 +296,7 @@ static TimeLineID curFileTLI;
 static XLogRecPtr ProcLastRecPtr = InvalidXLogRecPtr;

 XLogRecPtr	XactLastRecEnd = InvalidXLogRecPtr;
+XLogRecPtr	XactLastCommitEnd = InvalidXLogRecPtr;

 /*
 * RedoRecPtr is this backend's local copy of the REDO record pointer
@@ -6211,6 +6213,11 @@ StartupXLOG(void)
 	 */
 	StartupMultiXact();

+	/*
+	 * Recover knowledge about replay progress of known replication partners.
+	 */
+	StartupReplicationOrigin();
+
 	/*
 	 * Initialize unlogged LSN. On a clean shutdown, it's restored from the
 	 * control file. On recovery, all unlogged relations are blown away, so
@@ -8394,6 +8401,7 @@ CheckPointGuts(XLogRecPtr checkPointRedo, int flags)
 	CheckPointSnapBuild();
 	CheckPointLogicalRewriteHeap();
 	CheckPointBuffers(flags);	/* performs all required fsyncs */
+	CheckPointReplicationOrigin();
 	/* We deliberately delay 2PC checkpointing as long as possible */
 	CheckPointTwoPhase(checkPointRedo);
 }
--- a/src/backend/access/transam/xloginsert.c
+++ b/src/backend/access/transam/xloginsert.c
@@ -26,6 +26,7 @@
 #include "catalog/pg_control.h"
 #include "common/pg_lzcompress.h"
 #include "miscadmin.h"
+#include "replication/origin.h"
 #include "storage/bufmgr.h"
 #include "storage/proc.h"
 #include "utils/memutils.h"
@@ -72,6 +73,9 @@ static XLogRecData *mainrdata_head;
 static XLogRecData *mainrdata_last = (XLogRecData *) &mainrdata_head;
 static uint32 mainrdata_len;	/* total # of bytes in chain */

+/* Should te in-progress insertion log the origin */
+static bool include_origin = false;
+
 /*
 * These are used to hold the record header while constructing a record.
 * 'hdr_scratch' is not a plain variable, but is palloc'd at initialization,
@@ -83,10 +87,12 @@ static uint32 mainrdata_len;	/* total # of bytes in chain */
 static XLogRecData hdr_rdt;
 static char *hdr_scratch = NULL;

+#define SizeOfXlogOrigin	(sizeof(RepOriginId) + sizeof(char))
+
 #define HEADER_SCRATCH_SIZE \
 	(SizeOfXLogRecord + \
 	 MaxSizeOfXLogRecordBlockHeader * (XLR_MAX_BLOCK_ID + 1) + \
-	 SizeOfXLogRecordDataHeaderLong)
+	 SizeOfXLogRecordDataHeaderLong + SizeOfXlogOrigin)

 /*
 * An array of XLogRecData structs, to hold registered data.
@@ -193,6 +199,7 @@ XLogResetInsertion(void)
 	max_registered_block_id = 0;
 	mainrdata_len = 0;
 	mainrdata_last = (XLogRecData *) &mainrdata_head;
+	include_origin = false;
 	begininsert_called = false;
 }

@@ -374,6 +381,16 @@ XLogRegisterBufData(uint8 block_id, char *data, int len)
 	regbuf->rdata_len += len;
 }

+/*
+ * Should this record include the replication origin if one is set up?
+ */
+void
+XLogIncludeOrigin(void)
+{
+	Assert(begininsert_called);
+	include_origin = true;
+}
+
 /*
 * Insert an XLOG record having the specified RMID and info bytes, with the
 * body of the record being the data and buffer references registered earlier
@@ -678,6 +695,14 @@ XLogRecordAssemble(RmgrId rmid, uint8 info,
 		scratch += sizeof(BlockNumber);
 	}

+	/* followed by the record's origin, if any */
+	if (include_origin && replorigin_sesssion_origin != InvalidRepOriginId)
+	{
+		*(scratch++) = XLR_BLOCK_ID_ORIGIN;
+		memcpy(scratch, &replorigin_sesssion_origin, sizeof(replorigin_sesssion_origin));
+		scratch += sizeof(replorigin_sesssion_origin);
+	}
+
 	/* followed by main data, if any */
 	if (mainrdata_len > 0)
 	{
--- a/src/backend/access/transam/xlogreader.c
+++ b/src/backend/access/transam/xlogreader.c
@@ -21,6 +21,7 @@
 #include "access/xlogreader.h"
 #include "catalog/pg_control.h"
 #include "common/pg_lzcompress.h"
+#include "replication/origin.h"

 static bool allocate_recordbuf(XLogReaderState *state, uint32 reclength);

@@ -975,6 +976,7 @@ DecodeXLogRecord(XLogReaderState *state, XLogRecord *record, char **errormsg)
 	ResetDecoder(state);

 	state->decoded_record = record;
+	state->record_origin = InvalidRepOriginId;

 	ptr = (char *) record;
 	ptr += SizeOfXLogRecord;
@@ -1009,6 +1011,10 @@ DecodeXLogRecord(XLogReaderState *state, XLogRecord *record, char **errormsg)
 			break;				/* by convention, the main data fragment is
 								 * always last */
 		}
+		else if (block_id == XLR_BLOCK_ID_ORIGIN)
+		{
+			COPY_HEADER_FIELD(&state->record_origin, sizeof(RepOriginId));
+		}
 		else if (block_id <= XLR_MAX_BLOCK_ID)
 		{
 			/* XLogRecordBlockHeader */
--- a/src/backend/catalog/Makefile
+++ b/src/backend/catalog/Makefile
@@ -39,7 +39,7 @@ POSTGRES_BKI_SRCS = $(addprefix $(top_srcdir)/src/include/catalog/,\
 	pg_ts_config.h pg_ts_config_map.h pg_ts_dict.h \
 	pg_ts_parser.h pg_ts_template.h pg_extension.h \
 	pg_foreign_data_wrapper.h pg_foreign_server.h pg_user_mapping.h \
-	pg_foreign_table.h pg_policy.h \
+	pg_foreign_table.h pg_policy.h pg_replication_origin.h \
 	pg_default_acl.h pg_seclabel.h pg_shseclabel.h pg_collation.h pg_range.h \
 	pg_transform.h \
 	toasting.h indexing.h \
--- a/src/backend/catalog/catalog.c
+++ b/src/backend/catalog/catalog.c
@@ -32,6 +32,7 @@
 #include "catalog/pg_namespace.h"
 #include "catalog/pg_pltemplate.h"
 #include "catalog/pg_db_role_setting.h"
+#include "catalog/pg_replication_origin.h"
 #include "catalog/pg_shdepend.h"
 #include "catalog/pg_shdescription.h"
 #include "catalog/pg_shseclabel.h"
@@ -224,7 +225,8 @@ IsSharedRelation(Oid relationId)
 		relationId == SharedDependRelationId ||
 		relationId == SharedSecLabelRelationId ||
 		relationId == TableSpaceRelationId ||
-		relationId == DbRoleSettingRelationId)
+		relationId == DbRoleSettingRelationId ||
+		relationId == ReplicationOriginRelationId)
 		return true;
 	/* These are their indexes (see indexing.h) */
 	if (relationId == AuthIdRolnameIndexId ||
@@ -240,7 +242,9 @@ IsSharedRelation(Oid relationId)
 		relationId == SharedSecLabelObjectIndexId ||
 		relationId == TablespaceOidIndexId ||
 		relationId == TablespaceNameIndexId ||
-		relationId == DbRoleSettingDatidRolidIndexId)
+		relationId == DbRoleSettingDatidRolidIndexId ||
+		relationId == ReplicationOriginIdentIndex ||
+		relationId == ReplicationOriginNameIndex)
 		return true;
 	/* These are their toast tables and toast indexes (see toasting.h) */
 	if (relationId == PgShdescriptionToastTable ||
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -778,6 +778,13 @@ CREATE VIEW pg_user_mappings AS

 REVOKE ALL on pg_user_mapping FROM public;

+
+CREATE VIEW pg_replication_origin_status AS
+    SELECT *
+    FROM pg_show_replication_origin_status();
+
+REVOKE ALL ON pg_replication_origin_status FROM public;
+
 --
 -- We have a few function definitions in here, too.
 -- At some point there might be enough to justify breaking them out into
--- a/src/backend/replication/logical/Makefile
+++ b/src/backend/replication/logical/Makefile
@@ -14,6 +14,7 @@ include $(top_builddir)/src/Makefile.global

 override CPPFLAGS := -I$(srcdir) $(CPPFLAGS)

-OBJS = decode.o logical.o logicalfuncs.o reorderbuffer.o snapbuild.o
+OBJS = decode.o logical.o logicalfuncs.o reorderbuffer.o origin.o \
+	snapbuild.o

 include $(top_srcdir)/src/backend/common.mk
--- a/src/backend/replication/logical/decode.c
+++ b/src/backend/replication/logical/decode.c
@@ -40,6 +40,7 @@
 #include "replication/decode.h"
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
+#include "replication/origin.h"
 #include "replication/snapbuild.h"

 #include "storage/standby.h"
@@ -131,6 +132,7 @@ LogicalDecodingProcessRecord(LogicalDecodingContext *ctx, XLogReaderState *recor
 		case RM_SPGIST_ID:
 		case RM_BRIN_ID:
 		case RM_COMMIT_TS_ID:
+		case RM_REPLORIGIN_ID:
 			break;
 		case RM_NEXT_ID:
 			elog(ERROR, "unexpected RM_NEXT_ID rmgr_id: %u", (RmgrIds) XLogRecGetRmid(buf.record));
@@ -422,6 +424,15 @@ DecodeHeapOp(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 	}
 }

+static inline bool
+FilterByOrigin(LogicalDecodingContext *ctx, RepOriginId origin_id)
+{
+	if (ctx->callbacks.filter_by_origin_cb == NULL)
+		return false;
+
+	return filter_by_origin_cb_wrapper(ctx, origin_id);
+}
+
 /*
 * Consolidated commit record handling between the different form of commit
 * records.
@@ -430,8 +441,17 @@ static void
 DecodeCommit(LogicalDecodingContext *ctx, XLogRecordBuffer *buf,
 			 xl_xact_parsed_commit *parsed, TransactionId xid)
 {
+	XLogRecPtr	origin_lsn = InvalidXLogRecPtr;
+	XLogRecPtr	commit_time = InvalidXLogRecPtr;
+	XLogRecPtr	origin_id = InvalidRepOriginId;
 	int			i;

+	if (parsed->xinfo & XACT_XINFO_HAS_ORIGIN)
+	{
+		origin_lsn = parsed->origin_lsn;
+		commit_time = parsed->origin_timestamp;
+	}
+
 	/*
 	 * Process invalidation messages, even if we're not interested in the
 	 * transaction's contents, since the various caches need to always be
@@ -452,12 +472,13 @@ DecodeCommit(LogicalDecodingContext *ctx, XLogRecordBuffer *buf,
 	 * the reorderbuffer to forget the content of the (sub-)transactions
 	 * if not.
 	 *
-	 * There basically two reasons we might not be interested in this
+	 * There can be several reasons we might not be interested in this
 	 * transaction:
 	 * 1) We might not be interested in decoding transactions up to this
 	 *	  LSN. This can happen because we previously decoded it and now just
 	 *	  are restarting or if we haven't assembled a consistent snapshot yet.
 	 * 2) The transaction happened in another database.
+	 * 3) The output plugin is not interested in the origin.
 	 *
 	 * We can't just use ReorderBufferAbort() here, because we need to execute
 	 * the transaction's invalidations.  This currently won't be needed if
@@ -472,7 +493,8 @@ DecodeCommit(LogicalDecodingContext *ctx, XLogRecordBuffer *buf,
 	 * ---
 	 */
 	if (SnapBuildXactNeedsSkip(ctx->snapshot_builder, buf->origptr) ||
-		(parsed->dbId != InvalidOid && parsed->dbId != ctx->slot->data.database))
+		(parsed->dbId != InvalidOid && parsed->dbId != ctx->slot->data.database) ||
+		FilterByOrigin(ctx, origin_id))
 	{
 		for (i = 0; i < parsed->nsubxacts; i++)
 		{
@@ -492,7 +514,7 @@ DecodeCommit(LogicalDecodingContext *ctx, XLogRecordBuffer *buf,

 	/* replay actions of all transaction + subtransactions in order */
 	ReorderBufferCommit(ctx->reorder, xid, buf->origptr, buf->endptr,
-						parsed->xact_time);
+						commit_time, origin_id, origin_lsn);
 }

 /*
@@ -537,8 +559,13 @@ DecodeInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 	if (target_node.dbNode != ctx->slot->data.database)
 		return;

+	/* output plugin doesn't look for this origin, no need to queue */
+	if (FilterByOrigin(ctx, XLogRecGetOrigin(r)))
+		return;
+
 	change = ReorderBufferGetChange(ctx->reorder);
 	change->action = REORDER_BUFFER_CHANGE_INSERT;
+	change->origin_id = XLogRecGetOrigin(r);
 	memcpy(&change->data.tp.relnode, &target_node, sizeof(RelFileNode));

 	if (xlrec->flags & XLOG_HEAP_CONTAINS_NEW_TUPLE)
@@ -579,8 +606,13 @@ DecodeUpdate(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 	if (target_node.dbNode != ctx->slot->data.database)
 		return;

+	/* output plugin doesn't look for this origin, no need to queue */
+	if (FilterByOrigin(ctx, XLogRecGetOrigin(r)))
+		return;
+
 	change = ReorderBufferGetChange(ctx->reorder);
 	change->action = REORDER_BUFFER_CHANGE_UPDATE;
+	change->origin_id = XLogRecGetOrigin(r);
 	memcpy(&change->data.tp.relnode, &target_node, sizeof(RelFileNode));

 	if (xlrec->flags & XLOG_HEAP_CONTAINS_NEW_TUPLE)
@@ -628,8 +660,13 @@ DecodeDelete(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 	if (target_node.dbNode != ctx->slot->data.database)
 		return;

+	/* output plugin doesn't look for this origin, no need to queue */
+	if (FilterByOrigin(ctx, XLogRecGetOrigin(r)))
+		return;
+
 	change = ReorderBufferGetChange(ctx->reorder);
 	change->action = REORDER_BUFFER_CHANGE_DELETE;
+	change->origin_id = XLogRecGetOrigin(r);

 	memcpy(&change->data.tp.relnode, &target_node, sizeof(RelFileNode));

@@ -673,6 +710,10 @@ DecodeMultiInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
 	if (rnode.dbNode != ctx->slot->data.database)
 		return;

+	/* output plugin doesn't look for this origin, no need to queue */
+	if (FilterByOrigin(ctx, XLogRecGetOrigin(r)))
+		return;
+
 	tupledata = XLogRecGetBlockData(r, 0, &tuplelen);

 	data = tupledata;
@@ -685,6 +726,8 @@ DecodeMultiInsert(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)

 		change = ReorderBufferGetChange(ctx->reorder);
 		change->action = REORDER_BUFFER_CHANGE_INSERT;
+		change->origin_id = XLogRecGetOrigin(r);
+
 		memcpy(&change->data.tp.relnode, &rnode, sizeof(RelFileNode));

 		/*
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -39,6 +39,7 @@
 #include "replication/decode.h"
 #include "replication/logical.h"
 #include "replication/reorderbuffer.h"
+#include "replication/origin.h"
 #include "replication/snapbuild.h"

 #include "storage/proc.h"
@@ -720,6 +721,34 @@ change_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn,
 	error_context_stack = errcallback.previous;
 }

+bool
+filter_by_origin_cb_wrapper(LogicalDecodingContext *ctx, RepOriginId origin_id)
+{
+	LogicalErrorCallbackState state;
+	ErrorContextCallback errcallback;
+	bool ret;
+
+	/* Push callback + info on the error context stack */
+	state.ctx = ctx;
+	state.callback_name = "shutdown";
+	state.report_location = InvalidXLogRecPtr;
+	errcallback.callback = output_plugin_error_callback;
+	errcallback.arg = (void *) &state;
+	errcallback.previous = error_context_stack;
+	error_context_stack = &errcallback;
+
+	/* set output state */
+	ctx->accept_writes = false;
+
+	/* do the actual work: call callback */
+	ret = ctx->callbacks.filter_by_origin_cb(ctx, origin_id);
+
+	/* Pop the error context stack */
+	error_context_stack = errcallback.previous;
+
+	return ret;
+}
+
 /*
 * Set the required catalog xmin horizon for historic snapshots in the current
 * replication slot.
--- a/src/backend/replication/logical/origin.c
+++ b/src/backend/replication/logical/origin.c
--- a/src/backend/replication/logical/reorderbuffer.c
+++ b/src/backend/replication/logical/reorderbuffer.c
@@ -1255,7 +1255,8 @@ ReorderBufferFreeSnap(ReorderBuffer *rb, Snapshot snap)
 void
 ReorderBufferCommit(ReorderBuffer *rb, TransactionId xid,
 					XLogRecPtr commit_lsn, XLogRecPtr end_lsn,
-					TimestampTz commit_time)
+					TimestampTz commit_time,
+					RepOriginId origin_id, XLogRecPtr origin_lsn)
 {
 	ReorderBufferTXN *txn;
 	volatile Snapshot snapshot_now;
@@ -1273,6 +1274,8 @@ ReorderBufferCommit(ReorderBuffer *rb, TransactionId xid,
 	txn->final_lsn = commit_lsn;
 	txn->end_lsn = end_lsn;
 	txn->commit_time = commit_time;
+	txn->origin_id = origin_id;
+	txn->origin_lsn = origin_lsn;

 	/* serialize the last bunch of changes if we need start earlier anyway */
 	if (txn->nentries_mem != txn->nentries)
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -31,6 +31,7 @@
 #include "replication/slot.h"
 #include "replication/walreceiver.h"
 #include "replication/walsender.h"
+#include "replication/origin.h"
 #include "storage/bufmgr.h"
 #include "storage/dsm.h"
 #include "storage/ipc.h"
@@ -132,6 +133,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port)
 		size = add_size(size, CheckpointerShmemSize());
 		size = add_size(size, AutoVacuumShmemSize());
 		size = add_size(size, ReplicationSlotsShmemSize());
+		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -238,6 +240,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port)
 	CheckpointerShmemInit();
 	AutoVacuumShmemInit();
 	ReplicationSlotsShmemInit();
+	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();

--- a/src/backend/utils/cache/syscache.c
+++ b/src/backend/utils/cache/syscache.c
@@ -54,6 +54,7 @@
 #include "catalog/pg_shdepend.h"
 #include "catalog/pg_shdescription.h"
 #include "catalog/pg_shseclabel.h"
+#include "catalog/pg_replication_origin.h"
 #include "catalog/pg_statistic.h"
 #include "catalog/pg_tablespace.h"
 #include "catalog/pg_transform.h"
@@ -621,6 +622,28 @@ static const struct cachedesc cacheinfo[] = {
 		},
 		128
 	},
+	{ReplicationOriginRelationId,		/* REPLORIGIDENT */
+		ReplicationOriginIdentIndex,
+		1,
+		{
+			Anum_pg_replication_origin_roident,
+			0,
+			0,
+			0
+		},
+		16
+	},
+	{ReplicationOriginRelationId,	/* REPLORIGNAME */
+		ReplicationOriginNameIndex,
+		1,
+		{
+			Anum_pg_replication_origin_roname,
+			0,
+			0,
+			0
+		},
+		16
+	},
 	{RewriteRelationId,			/* RULERELNAME */
 		RewriteRelRulenameIndexId,
 		2,
--- a/src/bin/pg_resetxlog/pg_resetxlog.c
+++ b/src/bin/pg_resetxlog/pg_resetxlog.c
@@ -56,6 +56,8 @@
 #include "common/restricted_token.h"
 #include "storage/large_object.h"
 #include "pg_getopt.h"
+#include "replication/logical.h"
+#include "replication/origin.h"


 static ControlFileData ControlFile;		/* pg_control values */
@@ -1091,6 +1093,7 @@ WriteEmptyXLOG(void)
 	record->xl_tot_len = SizeOfXLogRecord + SizeOfXLogRecordDataHeaderShort + sizeof(CheckPoint);
 	record->xl_info = XLOG_CHECKPOINT_SHUTDOWN;
 	record->xl_rmid = RM_XLOG_ID;
+
 	recptr += SizeOfXLogRecord;
 	*(recptr++) = XLR_BLOCK_ID_DATA_SHORT;
 	*(recptr++) = sizeof(CheckPoint);
--- a/src/include/access/commit_ts.h
+++ b/src/include/access/commit_ts.h
@@ -13,6 +13,7 @@

 #include "access/xlog.h"
 #include "datatype/timestamp.h"
+#include "replication/origin.h"
 #include "utils/guc.h"


@@ -21,18 +22,13 @@ extern PGDLLIMPORT bool	track_commit_timestamp;
 extern bool check_track_commit_timestamp(bool *newval, void **extra,
 							 GucSource source);

-typedef uint32 CommitTsNodeId;
-#define InvalidCommitTsNodeId 0
-
-extern void CommitTsSetDefaultNodeId(CommitTsNodeId nodeid);
-extern CommitTsNodeId CommitTsGetDefaultNodeId(void);
 extern void TransactionTreeSetCommitTsData(TransactionId xid, int nsubxids,
 							   TransactionId *subxids, TimestampTz timestamp,
-							   CommitTsNodeId nodeid, bool do_xlog);
+							   RepOriginId nodeid, bool do_xlog);
 extern bool TransactionIdGetCommitTsData(TransactionId xid,
-							 TimestampTz *ts, CommitTsNodeId *nodeid);
+							 TimestampTz *ts, RepOriginId *nodeid);
 extern TransactionId GetLatestCommitTsData(TimestampTz *ts,
-					  CommitTsNodeId *nodeid);
+					  RepOriginId *nodeid);

 extern Size CommitTsShmemBuffers(void);
 extern Size CommitTsShmemSize(void);
@@ -58,7 +54,7 @@ extern void AdvanceOldestCommitTs(TransactionId oldestXact);
 typedef struct xl_commit_ts_set
 {
 	TimestampTz		timestamp;
-	CommitTsNodeId	nodeid;
+	RepOriginId		nodeid;
 	TransactionId	mainxid;
 	/* subxact Xids follow */
 } xl_commit_ts_set;
--- a/src/include/access/rmgrlist.h
+++ b/src/include/access/rmgrlist.h
@@ -44,3 +44,4 @@ PG_RMGR(RM_SEQ_ID, "Sequence", seq_redo, seq_desc, seq_identify, NULL, NULL)
 PG_RMGR(RM_SPGIST_ID, "SPGist", spg_redo, spg_desc, spg_identify, spg_xlog_startup, spg_xlog_cleanup)
 PG_RMGR(RM_BRIN_ID, "BRIN", brin_redo, brin_desc, brin_identify, NULL, NULL)
 PG_RMGR(RM_COMMIT_TS_ID, "CommitTs", commit_ts_redo, commit_ts_desc, commit_ts_identify, NULL, NULL)
+PG_RMGR(RM_REPLORIGIN_ID, "ReplicationOrigin", replorigin_redo, replorigin_desc, replorigin_identify, NULL, NULL)
--- a/src/include/access/xact.h
+++ b/src/include/access/xact.h
@@ -131,6 +131,7 @@ typedef void (*SubXactCallback) (SubXactEvent event, SubTransactionId mySubid,
 #define XACT_XINFO_HAS_RELFILENODES		(1U << 2)
 #define XACT_XINFO_HAS_INVALS			(1U << 3)
 #define XACT_XINFO_HAS_TWOPHASE			(1U << 4)
+#define XACT_XINFO_HAS_ORIGIN			(1U << 5)

 /*
 * Also stored in xinfo, these indicating a variety of additional actions that
@@ -217,6 +218,12 @@ typedef struct xl_xact_twophase
 } xl_xact_twophase;
 #define MinSizeOfXactInvals offsetof(xl_xact_invals, msgs)

+typedef struct xl_xact_origin
+{
+	XLogRecPtr	origin_lsn;
+	TimestampTz origin_timestamp;
+} xl_xact_origin;
+
 typedef struct xl_xact_commit
 {
 	TimestampTz xact_time;		/* time of commit */
@@ -227,6 +234,7 @@ typedef struct xl_xact_commit
 	/* xl_xact_relfilenodes follows if XINFO_HAS_RELFILENODES */
 	/* xl_xact_invals follows if XINFO_HAS_INVALS */
 	/* xl_xact_twophase follows if XINFO_HAS_TWOPHASE */
+	/* xl_xact_origin follows if XINFO_HAS_ORIGIN */
 } xl_xact_commit;
 #define MinSizeOfXactCommit (offsetof(xl_xact_commit, xact_time) + sizeof(TimestampTz))

@@ -267,6 +275,9 @@ typedef struct xl_xact_parsed_commit
 	SharedInvalidationMessage *msgs;

 	TransactionId	twophase_xid;	/* only for 2PC */
+
+	XLogRecPtr	origin_lsn;
+	TimestampTz origin_timestamp;
 } xl_xact_parsed_commit;

 typedef struct xl_xact_parsed_abort
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -85,6 +85,7 @@ typedef enum
 } RecoveryTargetType;

 extern XLogRecPtr XactLastRecEnd;
+extern PGDLLIMPORT XLogRecPtr XactLastCommitEnd;

 extern bool reachedConsistency;

--- 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 0xD083	/* can be used as WAL version indicator */
+#define XLOG_PAGE_MAGIC 0xD085	/* can be used as WAL version indicator */

 typedef struct XLogPageHeaderData
 {
--- a/src/include/access/xlogdefs.h
+++ b/src/include/access/xlogdefs.h
@@ -44,6 +44,12 @@ typedef uint64 XLogSegNo;
 */
 typedef uint32 TimeLineID;

+/*
+ * Replication origin id - this is located in this file to avoid having to
+ * include origin.h in a bunch of xlog related places.
+ */
+typedef uint16 RepOriginId;
+
 /*
 *	Because O_DIRECT bypasses the kernel buffers, and because we never
 *	read those buffers except during crash recovery or if wal_level != minimal,
--- a/src/include/access/xloginsert.h
+++ b/src/include/access/xloginsert.h
@@ -39,6 +39,7 @@

 /* prototypes for public functions in xloginsert.c: */
 extern void XLogBeginInsert(void);
+extern void XLogIncludeOrigin(void);
 extern XLogRecPtr XLogInsert(RmgrId rmid, uint8 info);
 extern void XLogEnsureRecordSpace(int nbuffers, int ndatas);
 extern void XLogRegisterData(char *data, int len);
--- a/src/include/access/xlogreader.h
+++ b/src/include/access/xlogreader.h
@@ -127,6 +127,8 @@ struct XLogReaderState
 	uint32		main_data_len;	/* main data portion's length */
 	uint32		main_data_bufsz;	/* allocated size of the buffer */

+	RepOriginId	record_origin;
+
 	/* information about blocks referenced by the record. */
 	DecodedBkpBlock blocks[XLR_MAX_BLOCK_ID + 1];

@@ -186,6 +188,7 @@ extern bool DecodeXLogRecord(XLogReaderState *state, XLogRecord *record,
 #define XLogRecGetInfo(decoder) ((decoder)->decoded_record->xl_info)
 #define XLogRecGetRmid(decoder) ((decoder)->decoded_record->xl_rmid)
 #define XLogRecGetXid(decoder) ((decoder)->decoded_record->xl_xid)
+#define XLogRecGetOrigin(decoder) ((decoder)->record_origin)
 #define XLogRecGetData(decoder) ((decoder)->main_data)
 #define XLogRecGetDataLen(decoder) ((decoder)->main_data_len)
 #define XLogRecHasAnyBlockRefs(decoder) ((decoder)->max_block_id >= 0)
--- a/src/include/access/xlogrecord.h
+++ b/src/include/access/xlogrecord.h
@@ -212,5 +212,6 @@ typedef struct XLogRecordDataHeaderLong

 #define XLR_BLOCK_ID_DATA_SHORT		255
 #define XLR_BLOCK_ID_DATA_LONG		254
+#define XLR_BLOCK_ID_ORIGIN			253

 #endif   /* XLOGRECORD_H */
--- a/src/include/catalog/catversion.h
+++ b/src/include/catalog/catversion.h
@@ -53,6 +53,6 @@
 */

 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	201504261
+#define CATALOG_VERSION_NO	201504291

 #endif
--- a/src/include/catalog/indexing.h
+++ b/src/include/catalog/indexing.h
@@ -310,6 +310,12 @@ DECLARE_UNIQUE_INDEX(pg_policy_oid_index, 3257, on pg_policy using btree(oid oid
 DECLARE_UNIQUE_INDEX(pg_policy_polrelid_polname_index, 3258, on pg_policy using btree(polrelid oid_ops, polname name_ops));
 #define PolicyPolrelidPolnameIndexId				3258

+DECLARE_UNIQUE_INDEX(pg_replication_origin_roiident_index, 6001, on pg_replication_origin using btree(roident oid_ops));
+#define ReplicationOriginIdentIndex 6001
+
+DECLARE_UNIQUE_INDEX(pg_replication_origin_roname_index, 6002, on pg_replication_origin using btree(roname varchar_pattern_ops));
+#define ReplicationOriginNameIndex 6002
+
 /* last step of initialization script: build the indexes declared above */
 BUILD_INDICES

--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -5203,6 +5203,42 @@ DESCR("for use by pg_upgrade");
 DATA(insert OID = 3591 ( binary_upgrade_create_empty_extension PGNSP PGUID  12 1 0 0 0 f f f f f f v 7 0 2278 "25 25 16 25 1028 1009 1009" _null_ _null_ _null_ _null_ _null_ binary_upgrade_create_empty_extension _null_ _null_ _null_ ));
 DESCR("for use by pg_upgrade");

+/* replication/origin.h */
+DATA(insert OID = 6003 ( pg_replication_origin_create PGNSP PGUID 12 1 0 0 0 f f f f t f v 1 0 26 "25" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_create _null_ _null_ _null_ ));
+DESCR("create a replication origin");
+
+DATA(insert OID = 6004 ( pg_replication_origin_drop PGNSP PGUID 12 1 0 0 0 f f f f t f v 1 0 2278 "25" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_drop _null_ _null_ _null_ ));
+DESCR("drop replication origin identified by its name");
+
+DATA(insert OID = 6005 ( pg_replication_origin_oid PGNSP PGUID 12 1 0 0 0 f f f f t f s 1 0 26 "25" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_oid _null_ _null_ _null_ ));
+DESCR("translate the replication origin's name to its id");
+
+DATA(insert OID = 6006 ( pg_replication_origin_session_setup PGNSP PGUID 12 1 0 0 0 f f f f t f v 1 0 2278 "25" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_session_setup _null_ _null_ _null_ ));
+DESCR("configure session to maintain replication progress tracking for the passed in origin");
+
+DATA(insert OID = 6007 ( pg_replication_origin_session_reset PGNSP PGUID 12 1 0 0 0 f f f f t f v 0 0 2278 "" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_session_reset _null_ _null_ _null_ ));
+DESCR("teardown configured replication progress tracking");
+
+DATA(insert OID = 6008 ( pg_replication_origin_session_is_setup PGNSP PGUID 12 1 0 0 0 f f f f t f v 0 0 16 "" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_session_is_setup _null_ _null_ _null_ ));
+DESCR("is a replication origin configured in this session");
+
+DATA(insert OID = 6009 ( pg_replication_origin_session_progress PGNSP PGUID 12 1 0 0 0 f f f f t f v 1 0 3220 "16" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_session_progress _null_ _null_ _null_ ));
+DESCR("get the replication progress of the current session");
+
+DATA(insert OID = 6010 ( pg_replication_origin_xact_setup PGNSP PGUID 12 1 0 0 0 f f f f t f v 2 0 2278 "3220 1184" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_xact_setup _null_ _null_ _null_ ));
+DESCR("setup the transaction's origin lsn and timestamp");
+
+DATA(insert OID = 6011 ( pg_replication_origin_xact_reset PGNSP PGUID 12 1 0 0 0 f f f f t f v 2 0 2278 "3220 1184" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_xact_reset _null_ _null_ _null_ ));
+DESCR("reset the transaction's origin lsn and timestamp");
+
+DATA(insert OID = 6012 ( pg_replication_origin_advance PGNSP PGUID 12 1 0 0 0 f f f f t f v 2 0 2278 "25 3220" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_advance _null_ _null_ _null_ ));
+DESCR("advance replication itentifier to specific location");
+
+DATA(insert OID = 6013 ( pg_replication_origin_progress PGNSP PGUID 12 1 0 0 0 f f f f t f v 2 0 3220 "25 16" _null_ _null_ _null_ _null_ _null_ pg_replication_origin_progress _null_ _null_ _null_ ));
+DESCR("get an individual replication origin's replication progress");
+
+DATA(insert OID = 6014 ( pg_show_replication_origin_status PGNSP PGUID 12 1 100 0 0 f f f f f t v 0 0 2249 "" "{26,25,3220,3220}" "{o,o,o,o}" "{local_id, external_id, remote_lsn, local_lsn}" _null_ _null_ pg_show_replication_origin_status _null_ _null_ _null_ ));
+DESCR("get progress for all replication origins");

 /*
 * Symbolic values for provolatile column: these indicate whether the result
--- a/src/include/catalog/pg_replication_origin.h
+++ b/src/include/catalog/pg_replication_origin.h
@@ -0,0 +1,70 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_replication_origin.h
+ *	  Persistent replication origin registry
+ *
+ * Portions Copyright (c) 1996-2015, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/catalog/pg_replication_origin.h
+ *
+ * NOTES
+ *	  the genbki.pl script reads this file and generates .bki
+ *	  information from the DATA() statements.
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_REPLICATION_ORIGIN_H
+#define PG_REPLICATION_ORIGIN_H
+
+#include "catalog/genbki.h"
+#include "access/xlogdefs.h"
+
+/* ----------------
+ *		pg_replication_origin.  cpp turns this into
+ *		typedef struct FormData_pg_replication_origin
+ * ----------------
+ */
+#define ReplicationOriginRelationId 6000
+
+CATALOG(pg_replication_origin,6000) BKI_SHARED_RELATION BKI_WITHOUT_OIDS
+{
+	/*
+	 * Locally known id that get included into WAL.
+	 *
+	 * This should never leave the system.
+	 *
+	 * Needs to fit into a uint16, so we don't waste too much space in WAL
+	 * records. For this reason we don't use a normal Oid column here, since
+	 * we need to handle allocation of new values manually.
+	 */
+	Oid		roident;
+
+	/*
+	 * Variable-length fields start here, but we allow direct access to
+	 * roname.
+	 */
+
+	/* external, free-format, name */
+	text	roname BKI_FORCE_NOT_NULL;
+
+#ifdef CATALOG_VARLEN		/* further variable-length fields */
+#endif
+} FormData_pg_replication_origin;
+
+typedef FormData_pg_replication_origin *Form_pg_replication_origin;
+
+/* ----------------
+ *		compiler constants for pg_replication_origin
+ * ----------------
+ */
+#define Natts_pg_replication_origin					2
+#define Anum_pg_replication_origin_roident			1
+#define Anum_pg_replication_origin_roname			2
+
+/* ----------------
+ *		pg_replication_origin has no initial contents
+ * ----------------
+ */
+
+#endif   /* PG_REPLICATION_ORIGIN_H */
--- a/src/include/replication/logical.h
+++ b/src/include/replication/logical.h
@@ -97,4 +97,6 @@ extern void LogicalIncreaseRestartDecodingForSlot(XLogRecPtr current_lsn,
 									  XLogRecPtr restart_lsn);
 extern void LogicalConfirmReceivedLocation(XLogRecPtr lsn);

+extern bool filter_by_origin_cb_wrapper(LogicalDecodingContext *ctx, RepOriginId origin_id);
+
 #endif
--- a/src/include/replication/origin.h
+++ b/src/include/replication/origin.h
@@ -0,0 +1,86 @@
+/*-------------------------------------------------------------------------
+ * origin.h
+ *     Exports from replication/logical/origin.c
+ *
+ * Copyright (c) 2013-2015, PostgreSQL Global Development Group
+ *
+ * src/include/replication/origin.h
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_ORIGIN_H
+#define PG_ORIGIN_H
+
+#include "access/xlogdefs.h"
+#include "catalog/pg_replication_origin.h"
+#include "replication/logical.h"
+
+typedef struct xl_replorigin_set
+{
+	XLogRecPtr	remote_lsn;
+	RepOriginId	node_id;
+	bool		force;
+} xl_replorigin_set;
+
+typedef struct xl_replorigin_drop
+{
+	RepOriginId	node_id;
+} xl_replorigin_drop;
+
+#define XLOG_REPLORIGIN_SET		0x00
+#define XLOG_REPLORIGIN_DROP		0x10
+
+#define InvalidRepOriginId 0
+#define DoNotReplicateId UINT16_MAX
+
+extern PGDLLIMPORT RepOriginId replorigin_sesssion_origin;
+extern PGDLLIMPORT XLogRecPtr replorigin_sesssion_origin_lsn;
+extern PGDLLIMPORT TimestampTz replorigin_sesssion_origin_timestamp;
+
+/* API for querying & manipulating replication origins */
+extern RepOriginId replorigin_by_name(char *name, bool missing_ok);
+extern RepOriginId replorigin_create(char *name);
+extern void replorigin_drop(RepOriginId roident);
+extern bool replorigin_by_oid(RepOriginId roident, bool missing_ok,
+								char **roname);
+
+/* API for querying & manipulating replication progress tracking */
+extern void replorigin_advance(RepOriginId node,
+							   XLogRecPtr remote_commit,
+							   XLogRecPtr local_commit,
+							   bool go_backward, bool wal_log);
+extern XLogRecPtr replorigin_get_progress(RepOriginId node, bool flush);
+
+extern void replorigin_session_advance(XLogRecPtr remote_commit,
+										XLogRecPtr local_commit);
+extern void replorigin_session_setup(RepOriginId node);
+extern void replorigin_session_reset(void);
+extern XLogRecPtr replorigin_session_get_progress(bool flush);
+
+/* Checkpoint/Startup integration */
+extern void CheckPointReplicationOrigin(void);
+extern void StartupReplicationOrigin(void);
+
+/* WAL logging */
+void replorigin_redo(XLogReaderState *record);
+void replorigin_desc(StringInfo buf, XLogReaderState *record);
+const char * replorigin_identify(uint8 info);
+
+/* shared memory allocation */
+extern Size ReplicationOriginShmemSize(void);
+extern void ReplicationOriginShmemInit(void);
+
+/* SQL callable functions */
+extern Datum pg_replication_origin_create(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_drop(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_oid(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_session_setup(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_session_reset(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_session_is_setup(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_session_progress(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_xact_setup(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_xact_reset(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_advance(PG_FUNCTION_ARGS);
+extern Datum pg_replication_origin_progress(PG_FUNCTION_ARGS);
+extern Datum pg_show_replication_origin_status(PG_FUNCTION_ARGS);
+
+#endif /* PG_ORIGIN_H */
--- a/src/include/replication/output_plugin.h
+++ b/src/include/replication/output_plugin.h
@@ -73,6 +73,13 @@ typedef void (*LogicalDecodeCommitCB) (
 												   ReorderBufferTXN *txn,
 												   XLogRecPtr commit_lsn);

+/*
+ * Filter changes by origin.
+ */
+typedef bool (*LogicalDecodeFilterByOriginCB) (
+											 struct LogicalDecodingContext *,
+												   RepOriginId origin_id);
+
 /*
 * Called to shutdown an output plugin.
 */
@@ -89,6 +96,7 @@ typedef struct OutputPluginCallbacks
 	LogicalDecodeBeginCB begin_cb;
 	LogicalDecodeChangeCB change_cb;
 	LogicalDecodeCommitCB commit_cb;
+	LogicalDecodeFilterByOriginCB filter_by_origin_cb;
 	LogicalDecodeShutdownCB shutdown_cb;
 } OutputPluginCallbacks;

--- a/src/include/replication/reorderbuffer.h
+++ b/src/include/replication/reorderbuffer.h
@@ -68,6 +68,8 @@ typedef struct ReorderBufferChange
 	/* The type of change. */
 	enum ReorderBufferChangeType action;

+	RepOriginId origin_id;
+
 	/*
 	 * Context data for the change, which part of the union is valid depends
 	 * on action/action_internal.
@@ -166,6 +168,10 @@ typedef struct ReorderBufferTXN
 	 */
 	XLogRecPtr	restart_decoding_lsn;

+	/* origin of the change that caused this transaction */
+	RepOriginId origin_id;
+	XLogRecPtr origin_lsn;
+
 	/*
 	 * Commit time, only known when we read the actual commit record.
 	 */
@@ -339,7 +345,7 @@ void		ReorderBufferReturnChange(ReorderBuffer *, ReorderBufferChange *);
 void		ReorderBufferQueueChange(ReorderBuffer *, TransactionId, XLogRecPtr lsn, ReorderBufferChange *);
 void ReorderBufferCommit(ReorderBuffer *, TransactionId,
 					XLogRecPtr commit_lsn, XLogRecPtr end_lsn,
-					TimestampTz commit_time);
+					TimestampTz commit_time, RepOriginId origin_id, XLogRecPtr origin_lsn);
 void		ReorderBufferAssignChild(ReorderBuffer *, TransactionId, TransactionId, XLogRecPtr commit_lsn);
 void ReorderBufferCommitChild(ReorderBuffer *, TransactionId, TransactionId,
 						 XLogRecPtr commit_lsn, XLogRecPtr end_lsn);
--- a/src/include/storage/lwlock.h
+++ b/src/include/storage/lwlock.h
@@ -134,8 +134,9 @@ extern PGDLLIMPORT LWLockPadded *MainLWLockArray;
 #define ReplicationSlotControlLock		(&MainLWLockArray[37].lock)
 #define CommitTsControlLock			(&MainLWLockArray[38].lock)
 #define CommitTsLock				(&MainLWLockArray[39].lock)
+#define ReplicationOriginLock		(&MainLWLockArray[40].lock)

-#define NUM_INDIVIDUAL_LWLOCKS		40
+#define NUM_INDIVIDUAL_LWLOCKS		41

 /*
 * It's a bit odd to declare NUM_BUFFER_PARTITIONS and NUM_LOCK_PARTITIONS
--- a/src/include/utils/syscache.h
+++ b/src/include/utils/syscache.h
@@ -77,6 +77,8 @@ enum SysCacheIdentifier
 	RANGETYPE,
 	RELNAMENSP,
 	RELOID,
+	REPLORIGIDENT,
+	REPLORIGNAME,
 	RULERELNAME,
 	STATRELATTINH,
 	TABLESPACEOID,
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1390,6 +1390,11 @@ pg_prepared_xacts| SELECT p.transaction,
   FROM ((pg_prepared_xact() p(transaction, gid, prepared, ownerid, dbid)
     LEFT JOIN pg_authid u ON ((p.ownerid = u.oid)))
     LEFT JOIN pg_database d ON ((p.dbid = d.oid)));
+pg_replication_origin_status| SELECT pg_show_replication_origin_status.local_id,
+    pg_show_replication_origin_status.external_id,
+    pg_show_replication_origin_status.remote_lsn,
+    pg_show_replication_origin_status.local_lsn
+   FROM pg_show_replication_origin_status() pg_show_replication_origin_status(local_id, external_id, remote_lsn, local_lsn);
 pg_replication_slots| SELECT l.slot_name,
    l.plugin,
    l.slot_type,
--- a/src/test/regress/expected/sanity_check.out
+++ b/src/test/regress/expected/sanity_check.out
@@ -121,6 +121,7 @@ pg_pltemplate|t
 pg_policy|t
 pg_proc|t
 pg_range|t
+pg_replication_origin|t
 pg_rewrite|t
 pg_seclabel|t
 pg_shdepend|t