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

1 files changed, 14 insertions, 39 deletions

diff --git a/src/backend/access/transam/commit_ts.c b/src/backend/access/transam/commit_ts.c
index dc23ab27b65..40042a5fd53 100644
--- 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;