5 files changed, 107 insertions, 61 deletions

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 0cfb2338aaa..1c90f8c3382 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -747,6 +747,7 @@ copy_heap_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex, bool verbose,
 	bool	   *isnull;
 	IndexScanDesc indexScan;
 	HeapScanDesc heapScan;
+	bool		use_wal;
 	bool		is_system_catalog;
 	TransactionId OldestXmin;
 	TransactionId FreezeXid;
@@ -802,9 +803,12 @@ copy_heap_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex, bool verbose,
 		LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock);
 
 	/*
-	 * Valid smgr_targblock implies something already wrote to the relation.
-	 * This may be harmless, but this function hasn't planned for it.
+	 * We need to log the copied data in WAL iff WAL archiving/streaming is
+	 * enabled AND it's a WAL-logged rel.
 	 */
+	use_wal = XLogIsNeeded() && RelationNeedsWAL(NewHeap);
+
+	/* use_wal off requires smgr_targblock be initially invalid */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
 	/*
@@ -872,7 +876,7 @@ copy_heap_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex, bool verbose,
 
 	/* Initialize the rewrite operation */
 	rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin, FreezeXid,
-								 MultiXactCutoff);
+								 MultiXactCutoff, use_wal);
 
 	/*
 	 * Decide whether to use an indexscan or seqscan-and-optional-sort to scan
@@ -1243,25 +1247,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	}
 
 	/*
-	 * Recognize that rel1's relfilenode (swapped from rel2) is new in this
-	 * subtransaction. The rel2 storage (swapped from rel1) may or may not be
-	 * new.
-	 */
-	{
-		Relation	rel1,
-					rel2;
-
-		rel1 = relation_open(r1, NoLock);
-		rel2 = relation_open(r2, NoLock);
-		rel2->rd_createSubid = rel1->rd_createSubid;
-		rel2->rd_newRelfilenodeSubid = rel1->rd_newRelfilenodeSubid;
-		rel2->rd_firstRelfilenodeSubid = rel1->rd_firstRelfilenodeSubid;
-		RelationAssumeNewRelfilenode(rel1);
-		relation_close(rel1, NoLock);
-		relation_close(rel2, NoLock);
-	}
-
-	/*
 	 * In the case of a shared catalog, these next few steps will only affect
 	 * our own database's pg_class row; but that's okay, because they are all
 	 * noncritical updates.  That's also an important fact for the case of a
diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c
index f053f70c6e2..9276f775c41 100644
--- a/src/backend/commands/copy.c
+++ b/src/backend/commands/copy.c
@@ -2274,14 +2274,49 @@ CopyFrom(CopyState cstate)
 
 	tupDesc = RelationGetDescr(cstate->rel);
 
-	/*
-	 * If the target file is new-in-transaction, we assume that checking FSM
-	 * for free space is a waste of time.  This could possibly be wrong, but
-	 * it's unlikely.
+	/*----------
+	 * Check to see if we can avoid writing WAL
+	 *
+	 * If archive logging/streaming is not enabled *and* either
+	 *	- table was created in same transaction as this COPY
+	 *	- data is being written to relfilenode created in this transaction
+	 * then we can skip writing WAL.  It's safe because if the transaction
+	 * doesn't commit, we'll discard the table (or the new relfilenode file).
+	 * If it does commit, we'll have done the heap_sync at the bottom of this
+	 * routine first.
+	 *
+	 * As mentioned in comments in utils/rel.h, the in-same-transaction test
+	 * is not always set correctly, since in rare cases rd_newRelfilenodeSubid
+	 * can be cleared before the end of the transaction. The exact case is
+	 * when a relation sets a new relfilenode twice in same transaction, yet
+	 * the second one fails in an aborted subtransaction, e.g.
+	 *
+	 * BEGIN;
+	 * TRUNCATE t;
+	 * SAVEPOINT save;
+	 * TRUNCATE t;
+	 * ROLLBACK TO save;
+	 * COPY ...
+	 *
+	 * Also, if the target file is new-in-transaction, we assume that checking
+	 * FSM for free space is a waste of time, even if we must use WAL because
+	 * of archiving.  This could possibly be wrong, but it's unlikely.
+	 *
+	 * The comments for heap_insert and RelationGetBufferForTuple specify that
+	 * skipping WAL logging is only safe if we ensure that our tuples do not
+	 * go into pages containing tuples from any other transactions --- but this
+	 * must be the case if we have a new table or new relfilenode, so we need
+	 * no additional work to enforce that.
+	 *----------
 	 */
+	/* createSubid is creation check, newRelfilenodeSubid is truncation check */
 	if (cstate->rel->rd_createSubid != InvalidSubTransactionId ||
-		cstate->rel->rd_firstRelfilenodeSubid != InvalidSubTransactionId)
+		cstate->rel->rd_newRelfilenodeSubid != InvalidSubTransactionId)
+	{
 		hi_options |= HEAP_INSERT_SKIP_FSM;
+		if (!XLogIsNeeded())
+			hi_options |= HEAP_INSERT_SKIP_WAL;
+	}
 
 	/*
 	 * Optimize if new relfilenode was created in this subxact or one of its
@@ -2540,6 +2575,13 @@ CopyFrom(CopyState cstate)
 
 	FreeExecutorState(estate);
 
+	/*
+	 * If we skipped writing WAL, then we need to sync the heap (but not
+	 * indexes since those use WAL anyway)
+	 */
+	if (hi_options & HEAP_INSERT_SKIP_WAL)
+		heap_sync(cstate->rel);
+
 	return processed;
 }
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 588a5acc108..e75b4fd65fe 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -561,13 +561,16 @@ intorel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
 	myState->rel = intoRelationDesc;
 	myState->reladdr = intoRelationAddr;
 	myState->output_cid = GetCurrentCommandId(true);
-	myState->hi_options = HEAP_INSERT_SKIP_FSM;
-	myState->bistate = GetBulkInsertState();
 
 	/*
-	 * Valid smgr_targblock implies something already wrote to the relation.
-	 * This may be harmless, but this function hasn't planned for it.
+	 * We can skip WAL-logging the insertions, unless PITR or streaming
+	 * replication is in use. We can skip the FSM in any case.
 	 */
+	myState->hi_options = HEAP_INSERT_SKIP_FSM |
+		(XLogIsNeeded() ? 0 : HEAP_INSERT_SKIP_WAL);
+	myState->bistate = GetBulkInsertState();
+
+	/* Not using WAL requires smgr_targblock be initially invalid */
 	Assert(RelationGetTargetBlock(intoRelationDesc) == InvalidBlockNumber);
 }
 
@@ -611,6 +614,10 @@ intorel_shutdown(DestReceiver *self)
 
 	FreeBulkInsertState(myState->bistate);
 
+	/* If we skipped using WAL, must heap_sync before commit */
+	if (myState->hi_options & HEAP_INSERT_SKIP_WAL)
+		heap_sync(myState->rel);
+
 	/* close rel, but keep lock until commit */
 	heap_close(myState->rel, NoLock);
 	myState->rel = NULL;
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 18492e763e0..ea6321fc132 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -403,13 +403,17 @@ transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
 	 */
 	myState->transientrel = transientrel;
 	myState->output_cid = GetCurrentCommandId(true);
-	myState->hi_options = HEAP_INSERT_SKIP_FSM | HEAP_INSERT_FROZEN;
-	myState->bistate = GetBulkInsertState();
 
 	/*
-	 * Valid smgr_targblock implies something already wrote to the relation.
-	 * This may be harmless, but this function hasn't planned for it.
+	 * We can skip WAL-logging the insertions, unless PITR or streaming
+	 * replication is in use. We can skip the FSM in any case.
 	 */
+	myState->hi_options = HEAP_INSERT_SKIP_FSM | HEAP_INSERT_FROZEN;
+	if (!XLogIsNeeded())
+		myState->hi_options |= HEAP_INSERT_SKIP_WAL;
+	myState->bistate = GetBulkInsertState();
+
+	/* Not using WAL requires smgr_targblock be initially invalid */
 	Assert(RelationGetTargetBlock(transientrel) == InvalidBlockNumber);
 }
 
@@ -447,6 +451,10 @@ transientrel_shutdown(DestReceiver *self)
 
 	FreeBulkInsertState(myState->bistate);
 
+	/* If we skipped using WAL, must heap_sync before commit */
+	if (myState->hi_options & HEAP_INSERT_SKIP_WAL)
+		heap_sync(myState->transientrel);
+
 	/* close transientrel, but keep lock until commit */
 	heap_close(myState->transientrel, NoLock);
 	myState->transientrel = NULL;
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 54cbbd4a4be..82004117522 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -4013,14 +4013,19 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap, LOCKMODE lockmode)
 		newrel = NULL;
 
 	/*
-	 * Prepare a BulkInsertState and options for heap_insert.  The FSM is
-	 * empty, so don't bother using it.
+	 * Prepare a BulkInsertState and options for heap_insert. Because we're
+	 * building a new heap, we can skip WAL-logging and fsync it to disk at
+	 * the end instead (unless WAL-logging is required for archiving or
+	 * streaming replication). The FSM is empty too, so don't bother using it.
 	 */
 	if (newrel)
 	{
 		mycid = GetCurrentCommandId(true);
 		bistate = GetBulkInsertState();
+
 		hi_options = HEAP_INSERT_SKIP_FSM;
+		if (!XLogIsNeeded())
+			hi_options |= HEAP_INSERT_SKIP_WAL;
 	}
 	else
 	{
@@ -4270,6 +4275,10 @@ ATRewriteTable(AlteredTableInfo *tab, Oid OIDNewHeap, LOCKMODE lockmode)
 	{
 		FreeBulkInsertState(bistate);
 
+		/* If we skipped writing WAL, then we need to sync the heap. */
+		if (hi_options & HEAP_INSERT_SKIP_WAL)
+			heap_sync(newrel);
+
 		heap_close(newrel, NoLock);
 	}
 }
@@ -5949,19 +5958,14 @@ ATExecAddIndex(AlteredTableInfo *tab, Relation rel,
 
 	/*
 	 * If TryReuseIndex() stashed a relfilenode for us, we used it for the new
-	 * index instead of building from scratch.  Restore associated fields.
-	 * This may store InvalidSubTransactionId in both fields, in which case
-	 * relcache.c will assume it can rebuild the relcache entry.  Hence, do
-	 * this after the CCI that made catalog rows visible to any rebuild.  The
-	 * DROP of the old edition of this index will have scheduled the storage
-	 * for deletion at commit, so cancel that pending deletion.
+	 * index instead of building from scratch.  The DROP of the old edition of
+	 * this index will have scheduled the storage for deletion at commit, so
+	 * cancel that pending deletion.
 	 */
 	if (OidIsValid(stmt->oldNode))
 	{
 		Relation	irel = index_open(address.objectId, NoLock);
 
-		irel->rd_createSubid = stmt->oldCreateSubid;
-		irel->rd_firstRelfilenodeSubid = stmt->oldFirstRelfilenodeSubid;
 		RelationPreserveStorage(irel->rd_node, true);
 		index_close(irel, NoLock);
 	}
@@ -9100,8 +9104,6 @@ TryReuseIndex(Oid oldId, IndexStmt *stmt)
 		Relation	irel = index_open(oldId, NoLock);
 
 		stmt->oldNode = irel->rd_node.relNode;
-		stmt->oldCreateSubid = irel->rd_createSubid;
-		stmt->oldFirstRelfilenodeSubid = irel->rd_firstRelfilenodeSubid;
 		index_close(irel, NoLock);
 	}
 }
@@ -9947,8 +9949,6 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode)
 
 	heap_close(pg_class, RowExclusiveLock);
 
-	RelationAssumeNewRelfilenode(rel);
-
 	relation_close(rel, NoLock);
 
 	/* Make sure the reltablespace change is visible */
@@ -10163,9 +10163,7 @@ copy_relation_data(SMgrRelation src, SMgrRelation dst,
 
 	/*
 	 * We need to log the copied data in WAL iff WAL archiving/streaming is
-	 * enabled AND it's a permanent relation.  This gives the same answer as
-	 * "RelationNeedsWAL(rel) || copying_initfork", because we know the
-	 * current operation created a new relfilenode.
+	 * enabled AND it's a permanent relation.
 	 */
 	use_wal = XLogIsNeeded() &&
 		(relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork);
@@ -10207,15 +10205,21 @@ copy_relation_data(SMgrRelation src, SMgrRelation dst,
 	}
 
 	/*
-	 * When we WAL-logged rel pages, we must nonetheless fsync them.  The
-	 * reason is that since we're copying outside shared buffers, a CHECKPOINT
-	 * occurring during the copy has no way to flush the previously written
-	 * data to disk (indeed it won't know the new rel even exists).  A crash
-	 * later on would replay WAL from the checkpoint, therefore it wouldn't
-	 * replay our earlier WAL entries. If we do not fsync those pages here,
-	 * they might still not be on disk when the crash occurs.
-	 */
-	if (use_wal || copying_initfork)
+	 * If the rel is WAL-logged, must fsync before commit.  We use heap_sync
+	 * to ensure that the toast table gets fsync'd too.  (For a temp or
+	 * unlogged rel we don't care since the data will be gone after a crash
+	 * anyway.)
+	 *
+	 * It's obvious that we must do this when not WAL-logging the copy. It's
+	 * less obvious that we have to do it even if we did WAL-log the copied
+	 * pages. The reason is that since we're copying outside shared buffers, a
+	 * CHECKPOINT occurring during the copy has no way to flush the previously
+	 * written data to disk (indeed it won't know the new rel even exists).  A
+	 * crash later on would replay WAL from the checkpoint, therefore it
+	 * wouldn't replay our earlier WAL entries. If we do not fsync those pages
+	 * here, they might still not be on disk when the crash occurs.
+	 */
+	if (relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork)
 		smgrimmedsync(dst, forkNum);
 }