Improve coding around the fsync request queue.

In all branches back to 8.3, this patch fixes a questionable assumption in
CompactCheckpointerRequestQueue/CompactBgwriterRequestQueue that there are
no uninitialized pad bytes in the request queue structs.  This would only
cause trouble if (a) there were such pad bytes, which could happen in 8.4
and up if the compiler makes enum ForkNumber narrower than 32 bits, but
otherwise would require not-currently-planned changes in the widths of
other typedefs; and (b) the kernel has not uniformly initialized the
contents of shared memory to zeroes.  Still, it seems a tad risky, and we
can easily remove any risk by pre-zeroing the request array for ourselves.
In addition to that, we need to establish a coding rule that struct
RelFileNode can't contain any padding bytes, since such structs are copied
into the request array verbatim.  (There are other places that are assuming
this anyway, it turns out.)

In 9.1 and up, the risk was a bit larger because we were also effectively
assuming that struct RelFileNodeBackend contained no pad bytes, and with
fields of different types in there, that would be much easier to break.
However, there is no good reason to ever transmit fsync or delete requests
for temp files to the bgwriter/checkpointer, so we can revert the request
structs to plain RelFileNode, getting rid of the padding risk and saving
some marginal number of bytes and cycles in fsync queue manipulation while
we are at it.  The savings might be more than marginal during deletion of
a temp relation, because the old code transmitted an entirely useless but
nonetheless expensive-to-process ForgetRelationFsync request to the
background process, and also had the background process perform the file
deletion even though that can safely be done immediately.

In addition, make some cleanup of nearby comments and small improvements to
the code in CompactCheckpointerRequestQueue/CompactBgwriterRequestQueue.

src/backend/storage/buffer/bufmgr.c

@@ -1971,7 +1971,8 @@ DropRelFileNodeBuffers(RelFileNodeBackend rnode, ForkNumber forkNum,
 {
 	int			i;
 
-	if (rnode.backend != InvalidBackendId)
+	/* If it's a local relation, it's localbuf.c's problem. */
+	if (RelFileNodeBackendIsTemp(rnode))
 	{
 		if (rnode.backend == MyBackendId)
 			DropRelFileNodeLocalBuffers(rnode.node, forkNum, firstDelBlock);

src/backend/storage/smgr/md.c

@@ -121,13 +121,17 @@ static MemoryContext MdCxt;		/* context for all md.c allocations */
  * be deleted after the next checkpoint, but we use a linked list instead of
  * a hash table, because we don't expect there to be any duplicate requests.
  *
+ * These mechanisms are only used for non-temp relations; we never fsync
+ * temp rels, nor do we need to postpone their deletion (see comments in
+ * mdunlink).
+ *
  * (Regular backends do not track pending operations locally, but forward
  * them to the bgwriter.)
  */
 typedef struct
 {
-	RelFileNodeBackend rnode;	/* the targeted relation */
-	ForkNumber	forknum;
+	RelFileNode	rnode;			/* the targeted relation */
+	ForkNumber	forknum;		/* which fork */
 	BlockNumber segno;			/* which segment */
 } PendingOperationTag;
 
@@ -142,7 +146,7 @@ typedef struct
 
 typedef struct
 {
-	RelFileNodeBackend rnode;	/* the dead relation to delete */
+	RelFileNode	rnode;			/* the dead relation to delete */
 	CycleCtr	cycle_ctr;		/* mdckpt_cycle_ctr when request was made */
 } PendingUnlinkEntry;
 
@@ -301,11 +305,11 @@ mdcreate(SMgrRelation reln, ForkNumber forkNum, bool isRedo)
 /*
  *	mdunlink() -- Unlink a relation.
  *
- * Note that we're passed a RelFileNode --- by the time this is called,
+ * Note that we're passed a RelFileNodeBackend --- by the time this is called,
  * there won't be an SMgrRelation hashtable entry anymore.
  *
- * Actually, we don't unlink the first segment file of the relation, but
- * just truncate it to zero length, and record a request to unlink it after
+ * For regular relations, we don't unlink the first segment file of the rel,
+ * but just truncate it to zero length, and record a request to unlink it after
  * the next checkpoint.  Additional segments can be unlinked immediately,
  * however.  Leaving the empty file in place prevents that relfilenode
  * number from being reused.  The scenario this protects us from is:
@@ -322,6 +326,12 @@ mdcreate(SMgrRelation reln, ForkNumber forkNum, bool isRedo)
  * number until it's safe, because relfilenode assignment skips over any
  * existing file.
  *
+ * We do not need to go through this dance for temp relations, though, because
+ * we never make WAL entries for temp rels, and so a temp rel poses no threat
+ * to the health of a regular rel that has taken over its relfilenode number.
+ * The fact that temp rels and regular rels have different file naming
+ * patterns provides additional safety.
+ *
  * All the above applies only to the relation's main fork; other forks can
  * just be removed immediately, since they are not needed to prevent the
  * relfilenode number from being recycled.  Also, we do not carefully
@@ -344,16 +354,18 @@ mdunlink(RelFileNodeBackend rnode, ForkNumber forkNum, bool isRedo)
 
 	/*
 	 * We have to clean out any pending fsync requests for the doomed
-	 * relation, else the next mdsync() will fail.
+	 * relation, else the next mdsync() will fail.  There can't be any such
+	 * requests for a temp relation, though.
 	 */
-	ForgetRelationFsyncRequests(rnode, forkNum);
+	if (!RelFileNodeBackendIsTemp(rnode))
+		ForgetRelationFsyncRequests(rnode.node, forkNum);
 
 	path = relpath(rnode, forkNum);
 
 	/*
 	 * Delete or truncate the first segment.
 	 */
-	if (isRedo || forkNum != MAIN_FORKNUM)
+	if (isRedo || forkNum != MAIN_FORKNUM || RelFileNodeBackendIsTemp(rnode))
 	{
 		ret = unlink(path);
 		if (ret < 0 && errno != ENOENT)
@@ -1078,8 +1090,7 @@ mdsync(void)
 				 * the relation will have been dirtied through this same smgr
 				 * relation, and so we can save a file open/close cycle.
 				 */
-				reln = smgropen(entry->tag.rnode.node,
-								entry->tag.rnode.backend);
+				reln = smgropen(entry->tag.rnode, InvalidBackendId);
 
 				/*
 				 * It is possible that the relation has been dropped or
@@ -1230,7 +1241,7 @@ mdpostckpt(void)
 		Assert((CycleCtr) (entry->cycle_ctr + 1) == mdckpt_cycle_ctr);
 
 		/* Unlink the file */
-		path = relpath(entry->rnode, MAIN_FORKNUM);
+		path = relpathperm(entry->rnode, MAIN_FORKNUM);
 		if (unlink(path) < 0)
 		{
 			/*
@@ -1258,20 +1269,23 @@ mdpostckpt(void)
  * If there is a local pending-ops table, just make an entry in it for
  * mdsync to process later.  Otherwise, try to pass off the fsync request
  * to the background writer process.  If that fails, just do the fsync
- * locally before returning (we expect this will not happen often enough
+ * locally before returning (we hope this will not happen often enough
  * to be a performance problem).
  */
 static void
 register_dirty_segment(SMgrRelation reln, ForkNumber forknum, MdfdVec *seg)
 {
+	/* Temp relations should never be fsync'd */
+	Assert(!SmgrIsTemp(reln));
+
 	if (pendingOpsTable)
 	{
 		/* push it into local pending-ops table */
-		RememberFsyncRequest(reln->smgr_rnode, forknum, seg->mdfd_segno);
+		RememberFsyncRequest(reln->smgr_rnode.node, forknum, seg->mdfd_segno);
 	}
 	else
 	{
-		if (ForwardFsyncRequest(reln->smgr_rnode, forknum, seg->mdfd_segno))
+		if (ForwardFsyncRequest(reln->smgr_rnode.node, forknum, seg->mdfd_segno))
 			return;				/* passed it off successfully */
 
 		ereport(DEBUG1,
@@ -1288,16 +1302,23 @@ register_dirty_segment(SMgrRelation reln, ForkNumber forknum, MdfdVec *seg)
 /*
  * register_unlink() -- Schedule a file to be deleted after next checkpoint
  *
+ * We don't bother passing in the fork number, because this is only used
+ * with main forks.
+ *
  * As with register_dirty_segment, this could involve either a local or
  * a remote pending-ops table.
  */
 static void
 register_unlink(RelFileNodeBackend rnode)
 {
+	/* Should never be used with temp relations */
+	Assert(!RelFileNodeBackendIsTemp(rnode));
+
 	if (pendingOpsTable)
 	{
 		/* push it into local pending-ops table */
-		RememberFsyncRequest(rnode, MAIN_FORKNUM, UNLINK_RELATION_REQUEST);
+		RememberFsyncRequest(rnode.node, MAIN_FORKNUM,
+							 UNLINK_RELATION_REQUEST);
 	}
 	else
 	{
@@ -1309,7 +1330,7 @@ register_unlink(RelFileNodeBackend rnode)
 		 * XXX should we just leave the file orphaned instead?
 		 */
 		Assert(IsUnderPostmaster);
-		while (!ForwardFsyncRequest(rnode, MAIN_FORKNUM,
+		while (!ForwardFsyncRequest(rnode.node, MAIN_FORKNUM,
 									UNLINK_RELATION_REQUEST))
 			pg_usleep(10000L);	/* 10 msec seems a good number */
 	}
@@ -1335,8 +1356,7 @@ register_unlink(RelFileNodeBackend rnode)
  * structure for them.)
  */
 void
-RememberFsyncRequest(RelFileNodeBackend rnode, ForkNumber forknum,
-					 BlockNumber segno)
+RememberFsyncRequest(RelFileNode rnode, ForkNumber forknum, BlockNumber segno)
 {
 	Assert(pendingOpsTable);
 
@@ -1349,7 +1369,7 @@ RememberFsyncRequest(RelFileNodeBackend rnode, ForkNumber forknum,
 		hash_seq_init(&hstat, pendingOpsTable);
 		while ((entry = (PendingOperationEntry *) hash_seq_search(&hstat)) != NULL)
 		{
-			if (RelFileNodeBackendEquals(entry->tag.rnode, rnode) &&
+			if (RelFileNodeEquals(entry->tag.rnode, rnode) &&
 				entry->tag.forknum == forknum)
 			{
 				/* Okay, cancel this entry */
@@ -1370,7 +1390,7 @@ RememberFsyncRequest(RelFileNodeBackend rnode, ForkNumber forknum,
 		hash_seq_init(&hstat, pendingOpsTable);
 		while ((entry = (PendingOperationEntry *) hash_seq_search(&hstat)) != NULL)
 		{
-			if (entry->tag.rnode.node.dbNode == rnode.node.dbNode)
+			if (entry->tag.rnode.dbNode == rnode.dbNode)
 			{
 				/* Okay, cancel this entry */
 				entry->canceled = true;
@@ -1384,7 +1404,7 @@ RememberFsyncRequest(RelFileNodeBackend rnode, ForkNumber forknum,
 			PendingUnlinkEntry *entry = (PendingUnlinkEntry *) lfirst(cell);
 
 			next = lnext(cell);
-			if (entry->rnode.node.dbNode == rnode.node.dbNode)
+			if (entry->rnode.dbNode == rnode.dbNode)
 			{
 				pendingUnlinks = list_delete_cell(pendingUnlinks, cell, prev);
 				pfree(entry);
@@ -1399,6 +1419,9 @@ RememberFsyncRequest(RelFileNodeBackend rnode, ForkNumber forknum,
 		MemoryContext oldcxt = MemoryContextSwitchTo(MdCxt);
 		PendingUnlinkEntry *entry;
 
+		/* PendingUnlinkEntry doesn't store forknum, since it's always MAIN */
+		Assert(forknum == MAIN_FORKNUM);
+
 		entry = palloc(sizeof(PendingUnlinkEntry));
 		entry->rnode = rnode;
 		entry->cycle_ctr = mdckpt_cycle_ctr;
@@ -1448,10 +1471,10 @@ RememberFsyncRequest(RelFileNodeBackend rnode, ForkNumber forknum,
 }
 
 /*
- * ForgetRelationFsyncRequests -- forget any fsyncs for a rel
+ * ForgetRelationFsyncRequests -- forget any fsyncs for a relation fork
  */
 void
-ForgetRelationFsyncRequests(RelFileNodeBackend rnode, ForkNumber forknum)
+ForgetRelationFsyncRequests(RelFileNode rnode, ForkNumber forknum)
 {
 	if (pendingOpsTable)
 	{
@@ -1486,12 +1509,11 @@ ForgetRelationFsyncRequests(RelFileNodeBackend rnode, ForkNumber forknum)
 void
 ForgetDatabaseFsyncRequests(Oid dbid)
 {
-	RelFileNodeBackend rnode;
+	RelFileNode rnode;
 
-	rnode.node.dbNode = dbid;
-	rnode.node.spcNode = 0;
-	rnode.node.relNode = 0;
-	rnode.backend = InvalidBackendId;
+	rnode.dbNode = dbid;
+	rnode.spcNode = 0;
+	rnode.relNode = 0;
 
 	if (pendingOpsTable)
 	{