Include the backend ID in the relpath of temporary relations.

This allows us to reliably remove all leftover temporary relation
files on cluster startup without reference to system catalogs or WAL;
therefore, we no longer include temporary relations in XLOG_XACT_COMMIT
and XLOG_XACT_ABORT WAL records.

Since these changes require including a backend ID in each
SharedInvalSmgrMsg, the size of the SharedInvalidationMessage.id
field has been reduced from two bytes to one, and the maximum number
of connections has been reduced from INT_MAX / 4 to 2^23-1.  It would
be possible to remove these restrictions by increasing the size of
SharedInvalidationMessage by 4 bytes, but right now that doesn't seem
like a good trade-off.

Review by Jaime Casanova and Tom Lane.

Author: robertmhaas

doc/src/sgml/storage.sgml

@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/storage.sgml,v 1.32 2010/02/16 22:34:43 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/storage.sgml,v 1.33 2010/08/13 20:10:50 rhaas Exp $ -->
 
 <chapter id="storage">
 
@@ -133,16 +133,20 @@ there.
 </para>
 
 <para>
-Each table and index is stored in a separate file, named after the table
-or index's <firstterm>filenode</> number, which can be found in
-<structname>pg_class</>.<structfield>relfilenode</>. In addition to the
-main file (a/k/a main fork), each table and index has a <firstterm>free space
-map</> (see <xref linkend="storage-fsm">), which stores information about free
-space available in the relation.  The free space map is stored in a file named
-with the filenode number plus the suffix <literal>_fsm</>.  Tables also have a
-<firstterm>visibility map</>, stored in a fork with the suffix
-<literal>_vm</>, to track which pages are known to have no dead tuples.
-The visibility map is described further in <xref linkend="storage-vm">.
+Each table and index is stored in a separate file.  For ordinary relations,
+these files are named after the table or index's <firstterm>filenode</> number,
+which can be found in <structname>pg_class</>.<structfield>relfilenode</>. But
+for temporary relations, the file name is of the form
+<literal>t<replaceable>BBB</>_<replaceable>FFF</></>, where <replaceable>BBB</>
+is the backend ID of the backend which created the file, and <replaceable>FFF</>
+is the filenode number.  In either case, in addition to the main file (a/k/a
+main fork), each table and index has a <firstterm>free space map</> (see <xref
+linkend="storage-fsm">), which stores information about free space available in
+the relation.  The free space map is stored in a file named with the filenode
+number plus the suffix <literal>_fsm</>.  Tables also have a
+<firstterm>visibility map</>, stored in a fork with the suffix <literal>_vm</>,
+to track which pages are known to have no dead tuples.  The visibility map is
+described further in <xref linkend="storage-vm">.
 </para>
 
 <caution>

src/backend/access/heap/visibilitymap.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/heap/visibilitymap.c,v 1.10 2010/04/23 23:21:44 rhaas Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/heap/visibilitymap.c,v 1.11 2010/08/13 20:10:50 rhaas Exp $
  *
  * INTERFACE ROUTINES
  *		visibilitymap_clear - clear a bit in the visibility map
@@ -373,8 +373,7 @@ visibilitymap_truncate(Relation rel, BlockNumber nheapblocks)
 	}
 
 	/* Truncate the unused VM pages, and send smgr inval message */
-	smgrtruncate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, newnblocks,
-				 rel->rd_istemp);
+	smgrtruncate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, newnblocks);
 
 	/*
 	 * We might as well update the local smgr_vm_nblocks setting. smgrtruncate

src/backend/access/nbtree/nbtsort.c

@@ -59,7 +59,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/nbtree/nbtsort.c,v 1.125 2010/04/28 16:10:40 heikki Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/nbtree/nbtsort.c,v 1.126 2010/08/13 20:10:50 rhaas Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -295,9 +295,8 @@ _bt_blwritepage(BTWriteState *wstate, Page page, BlockNumber blkno)
 	}
 
 	/*
-	 * Now write the page.	We say isTemp = true even if it's not a temp
-	 * index, because there's no need for smgr to schedule an fsync for this
-	 * write; we'll do it ourselves before ending the build.
+	 * Now write the page.	There's no need for smgr to schedule an fsync for
+	 * this write; we'll do it ourselves before ending the build.
 	 */
 	if (blkno == wstate->btws_pages_written)
 	{

src/backend/access/transam/twophase.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *		$PostgreSQL: pgsql/src/backend/access/transam/twophase.c,v 1.62 2010/07/06 19:18:55 momjian Exp $
+ *		$PostgreSQL: pgsql/src/backend/access/transam/twophase.c,v 1.63 2010/08/13 20:10:50 rhaas Exp $
  *
  * NOTES
  *		Each global transaction is associated with a global transaction
@@ -865,8 +865,8 @@ StartPrepare(GlobalTransaction gxact)
 	hdr.prepared_at = gxact->prepared_at;
 	hdr.owner = gxact->owner;
 	hdr.nsubxacts = xactGetCommittedChildren(&children);
-	hdr.ncommitrels = smgrGetPendingDeletes(true, &commitrels, NULL);
-	hdr.nabortrels = smgrGetPendingDeletes(false, &abortrels, NULL);
+	hdr.ncommitrels = smgrGetPendingDeletes(true, &commitrels);
+	hdr.nabortrels = smgrGetPendingDeletes(false, &abortrels);
 	hdr.ninvalmsgs = xactGetCommittedInvalidationMessages(&invalmsgs,
 														  &hdr.initfileinval);
 	StrNCpy(hdr.gid, gxact->gid, GIDSIZE);
@@ -1320,13 +1320,13 @@ FinishPreparedTransaction(const char *gid, bool isCommit)
 	}
 	for (i = 0; i < ndelrels; i++)
 	{
-		SMgrRelation srel = smgropen(delrels[i]);
+		SMgrRelation srel = smgropen(delrels[i], InvalidBackendId);
 		ForkNumber	fork;
 
 		for (fork = 0; fork <= MAX_FORKNUM; fork++)
 		{
 			if (smgrexists(srel, fork))
-				smgrdounlink(srel, fork, false, false);
+				smgrdounlink(srel, fork, false);
 		}
 		smgrclose(srel);
 	}

src/backend/access/transam/xact.c

@@ -10,7 +10,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/transam/xact.c,v 1.297 2010/08/13 15:42:21 rhaas Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/transam/xact.c,v 1.298 2010/08/13 20:10:50 rhaas Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -912,15 +912,14 @@ RecordTransactionCommit(void)
 	TransactionId latestXid = InvalidTransactionId;
 	int			nrels;
 	RelFileNode *rels;
-	bool		haveNonTemp;
 	int			nchildren;
 	TransactionId *children;
 	int			nmsgs = 0;
 	SharedInvalidationMessage *invalMessages = NULL;
 	bool		RelcacheInitFileInval = false;
 
 	/* Get data needed for commit record */
-	nrels = smgrGetPendingDeletes(true, &rels, &haveNonTemp);
+	nrels = smgrGetPendingDeletes(true, &rels);
 	nchildren = xactGetCommittedChildren(&children);
 	if (XLogStandbyInfoActive())
 		nmsgs = xactGetCommittedInvalidationMessages(&invalMessages,
@@ -1048,7 +1047,7 @@ RecordTransactionCommit(void)
 	 * asynchronous commit if all to-be-deleted tables are temporary though,
 	 * since they are lost anyway if we crash.)
 	 */
-	if (XactSyncCommit || forceSyncCommit || haveNonTemp)
+	if (XactSyncCommit || forceSyncCommit || nrels > 0)
 	{
 		/*
 		 * Synchronous commit case:
@@ -1334,7 +1333,7 @@ RecordTransactionAbort(bool isSubXact)
 			 xid);
 
 	/* Fetch the data we need for the abort record */
-	nrels = smgrGetPendingDeletes(false, &rels, NULL);
+	nrels = smgrGetPendingDeletes(false, &rels);
 	nchildren = xactGetCommittedChildren(&children);
 
 	/* XXX do we really need a critical section here? */
@@ -4474,15 +4473,15 @@ xact_redo_commit(xl_xact_commit *xlrec, TransactionId xid, XLogRecPtr lsn)
 	/* Make sure files supposed to be dropped are dropped */
 	for (i = 0; i < xlrec->nrels; i++)
 	{
-		SMgrRelation srel = smgropen(xlrec->xnodes[i]);
+		SMgrRelation srel = smgropen(xlrec->xnodes[i], InvalidBackendId);
 		ForkNumber	fork;
 
 		for (fork = 0; fork <= MAX_FORKNUM; fork++)
 		{
 			if (smgrexists(srel, fork))
 			{
 				XLogDropRelation(xlrec->xnodes[i], fork);
-				smgrdounlink(srel, fork, false, true);
+				smgrdounlink(srel, fork, true);
 			}
 		}
 		smgrclose(srel);
@@ -4579,15 +4578,15 @@ xact_redo_abort(xl_xact_abort *xlrec, TransactionId xid)
 	/* Make sure files supposed to be dropped are dropped */
 	for (i = 0; i < xlrec->nrels; i++)
 	{
-		SMgrRelation srel = smgropen(xlrec->xnodes[i]);
+		SMgrRelation srel = smgropen(xlrec->xnodes[i], InvalidBackendId);
 		ForkNumber	fork;
 
 		for (fork = 0; fork <= MAX_FORKNUM; fork++)
 		{
 			if (smgrexists(srel, fork))
 			{
 				XLogDropRelation(xlrec->xnodes[i], fork);
-				smgrdounlink(srel, fork, false, true);
+				smgrdounlink(srel, fork, true);
 			}
 		}
 		smgrclose(srel);
@@ -4661,7 +4660,7 @@ xact_desc_commit(StringInfo buf, xl_xact_commit *xlrec)
 		appendStringInfo(buf, "; rels:");
 		for (i = 0; i < xlrec->nrels; i++)
 		{
-			char	   *path = relpath(xlrec->xnodes[i], MAIN_FORKNUM);
+			char	   *path = relpathperm(xlrec->xnodes[i], MAIN_FORKNUM);
 
 			appendStringInfo(buf, " %s", path);
 			pfree(path);
@@ -4716,7 +4715,7 @@ xact_desc_abort(StringInfo buf, xl_xact_abort *xlrec)
 		appendStringInfo(buf, "; rels:");
 		for (i = 0; i < xlrec->nrels; i++)
 		{
-			char	   *path = relpath(xlrec->xnodes[i], MAIN_FORKNUM);
+			char	   *path = relpathperm(xlrec->xnodes[i], MAIN_FORKNUM);
 
 			appendStringInfo(buf, " %s", path);
 			pfree(path);

src/backend/access/transam/xlogutils.c

@@ -11,7 +11,7 @@
  * Portions Copyright (c) 1996-2010, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/backend/access/transam/xlogutils.c,v 1.71 2010/07/08 16:08:30 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/access/transam/xlogutils.c,v 1.72 2010/08/13 20:10:50 rhaas Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -68,7 +68,7 @@ log_invalid_page(RelFileNode node, ForkNumber forkno, BlockNumber blkno,
 	 */
 	if (log_min_messages <= DEBUG1 || client_min_messages <= DEBUG1)
 	{
-		char	   *path = relpath(node, forkno);
+		char	   *path = relpathperm(node, forkno);
 
 		if (present)
 			elog(DEBUG1, "page %u of relation %s is uninitialized",
@@ -133,7 +133,7 @@ forget_invalid_pages(RelFileNode node, ForkNumber forkno, BlockNumber minblkno)
 		{
 			if (log_min_messages <= DEBUG2 || client_min_messages <= DEBUG2)
 			{
-				char	   *path = relpath(hentry->key.node, forkno);
+				char	   *path = relpathperm(hentry->key.node, forkno);
 
 				elog(DEBUG2, "page %u of relation %s has been dropped",
 					 hentry->key.blkno, path);
@@ -166,7 +166,7 @@ forget_invalid_pages_db(Oid dbid)
 		{
 			if (log_min_messages <= DEBUG2 || client_min_messages <= DEBUG2)
 			{
-				char	   *path = relpath(hentry->key.node, hentry->key.forkno);
+				char	   *path = relpathperm(hentry->key.node, hentry->key.forkno);
 
 				elog(DEBUG2, "page %u of relation %s has been dropped",
 					 hentry->key.blkno, path);
@@ -200,7 +200,7 @@ XLogCheckInvalidPages(void)
 	 */
 	while ((hentry = (xl_invalid_page *) hash_seq_search(&status)) != NULL)
 	{
-		char	   *path = relpath(hentry->key.node, hentry->key.forkno);
+		char	   *path = relpathperm(hentry->key.node, hentry->key.forkno);
 
 		if (hentry->present)
 			elog(WARNING, "page %u of relation %s was uninitialized",
@@ -276,7 +276,7 @@ XLogReadBufferExtended(RelFileNode rnode, ForkNumber forknum,
 	Assert(blkno != P_NEW);
 
 	/* Open the relation at smgr level */
-	smgr = smgropen(rnode);
+	smgr = smgropen(rnode, InvalidBackendId);
 
 	/*
 	 * Create the target file if it doesn't already exist.  This lets us cope
@@ -293,7 +293,7 @@ XLogReadBufferExtended(RelFileNode rnode, ForkNumber forknum,
 	if (blkno < lastblock)
 	{
 		/* page exists in file */
-		buffer = ReadBufferWithoutRelcache(rnode, false, forknum, blkno,
+		buffer = ReadBufferWithoutRelcache(rnode, forknum, blkno,
 										   mode, NULL);
 	}
 	else
@@ -312,7 +312,7 @@ XLogReadBufferExtended(RelFileNode rnode, ForkNumber forknum,
 		{
 			if (buffer != InvalidBuffer)
 				ReleaseBuffer(buffer);
-			buffer = ReadBufferWithoutRelcache(rnode, false, forknum,
+			buffer = ReadBufferWithoutRelcache(rnode, forknum,
 											   P_NEW, mode, NULL);
 			lastblock++;
 		}