Fix another bug in parent page splitting during GiST index build.

hlinnaka · hlinnaka · commit 26917ebea745 · 2023-09-26T15:41:44.000+03:00
Yet another bug in the ilk of commits a7ee7c8 and 741b884. In 741b884, we took care to clear the memorized location of the downlink when we split the parent page, because splitting the parent page can move the downlink. But we missed that even *updating* a tuple on the parent can move it, because updating a tuple on a gist page is implemented as a delete+insert, so the updated tuple gets moved to the end of the page. This commit fixes the bug in two different ways (belt and suspenders): 1. Clear the downlink when we update a tuple on the parent page, even if it's not split. This the same approach as in commits a7ee7c8 and 741b884. I also noticed that gistFindCorrectParent did not clear the 'downlinkoffnum' when it stepped to the right sibling. Fix that too, as it seems like a clear bug even though I haven't been able to find a test case to hit that. 2. Change gistFindCorrectParent so that it treats 'downlinkoffnum' merely as a hint. It now always first checks if the downlink is still at that location, and if not, it scans the page like before. That's more robust if there are still more cases where we fail to clear 'downlinkoffnum' that we haven't yet uncovered. With this, it's no longer necessary to meticulously clear 'downlinkoffnum', so this makes the previous fixes unnecessary, but I didn't revert them because it still seems nice to clear it when we know that the downlink has moved. Also add the test case using the same test data that Alexander posted. I tried to reduce it to a smaller test, and I also tried to reproduce this with different test data, but I was not able to, so let's just include what we have. Backpatch to v12, like the previous fixes. Reported-by: Alexander Lakhin Discussion: https://www.postgresql.org/message-id/18129-caca016eaf0c3702@postgresql.org
diff --git a/src/backend/access/gist/gist.c b/src/backend/access/gist/gist.c
@@ -1011,97 +1011,114 @@ gistFindPath(Relation r, BlockNumber child, OffsetNumber *downlinkoffnum)
  * remain so at exit, but it might not be the same page anymore.
  */
 static void
-gistFindCorrectParent(Relation r, GISTInsertStack *child)
+gistFindCorrectParent(Relation r, GISTInsertStack *child, bool is_build)
 {
 	GISTInsertStack *parent = child->parent;
+	ItemId		iid;
+	IndexTuple	idxtuple;
+	OffsetNumber maxoff;
+	GISTInsertStack *ptr;
 
 	gistcheckpage(r, parent->buffer);
 	parent->page = (Page) BufferGetPage(parent->buffer);
+	maxoff = PageGetMaxOffsetNumber(parent->page);
 
-	/* here we don't need to distinguish between split and page update */
-	if (child->downlinkoffnum == InvalidOffsetNumber ||
-		parent->lsn != PageGetLSN(parent->page))
+	/* Check if the downlink is still where it was before */
+	if (child->downlinkoffnum != InvalidOffsetNumber && child->downlinkoffnum <= maxoff)
 	{
-		/* parent is changed, look child in right links until found */
-		OffsetNumber i,
-					maxoff;
-		ItemId		iid;
-		IndexTuple	idxtuple;
-		GISTInsertStack *ptr;
+		iid = PageGetItemId(parent->page, child->downlinkoffnum);
+		idxtuple = (IndexTuple) PageGetItem(parent->page, iid);
+		if (ItemPointerGetBlockNumber(&(idxtuple->t_tid)) == child->blkno)
+			return;				/* still there */
+	}
 
-		while (true)
-		{
-			maxoff = PageGetMaxOffsetNumber(parent->page);
-			for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
-			{
-				iid = PageGetItemId(parent->page, i);
-				idxtuple = (IndexTuple) PageGetItem(parent->page, iid);
-				if (ItemPointerGetBlockNumber(&(idxtuple->t_tid)) == child->blkno)
-				{
-					/* yes!!, found */
-					child->downlinkoffnum = i;
-					return;
-				}
-			}
+	/*
+	 * The page has changed since we looked. During normal operation, every
+	 * update of a page changes its LSN, so the LSN we memorized should have
+	 * changed too. During index build, however, we don't WAL-log the changes
+	 * until we have built the index, so the LSN doesn't change. There is no
+	 * concurrent activity during index build, but we might have changed the
+	 * parent ourselves.
+	 */
+	Assert(parent->lsn != PageGetLSN(parent->page) || is_build);
+
+	/*
+	 * Scan the page to re-find the downlink. If the page was split, it might
+	 * have moved to a different page, so follow the right links until we find
+	 * it.
+	 */
+	while (true)
+	{
+		OffsetNumber i;
 
-			parent->blkno = GistPageGetOpaque(parent->page)->rightlink;
-			UnlockReleaseBuffer(parent->buffer);
-			if (parent->blkno == InvalidBlockNumber)
+		maxoff = PageGetMaxOffsetNumber(parent->page);
+		for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
+		{
+			iid = PageGetItemId(parent->page, i);
+			idxtuple = (IndexTuple) PageGetItem(parent->page, iid);
+			if (ItemPointerGetBlockNumber(&(idxtuple->t_tid)) == child->blkno)
 			{
-				/*
-				 * End of chain and still didn't find parent. It's a very-very
-				 * rare situation when root splited.
-				 */
-				break;
+				/* yes!!, found */
+				child->downlinkoffnum = i;
+				return;
 			}
-			parent->buffer = ReadBuffer(r, parent->blkno);
-			LockBuffer(parent->buffer, GIST_EXCLUSIVE);
-			gistcheckpage(r, parent->buffer);
-			parent->page = (Page) BufferGetPage(parent->buffer);
 		}
 
-		/*
-		 * awful!!, we need search tree to find parent ... , but before we
-		 * should release all old parent
-		 */
-
-		ptr = child->parent->parent;	/* child->parent already released
-										 * above */
-		while (ptr)
+		parent->blkno = GistPageGetOpaque(parent->page)->rightlink;
+		parent->downlinkoffnum = InvalidOffsetNumber;
+		UnlockReleaseBuffer(parent->buffer);
+		if (parent->blkno == InvalidBlockNumber)
 		{
-			ReleaseBuffer(ptr->buffer);
-			ptr = ptr->parent;
+			/*
+			 * End of chain and still didn't find parent. It's a very-very
+			 * rare situation when root splitted.
+			 */
+			break;
 		}
+		parent->buffer = ReadBuffer(r, parent->blkno);
+		LockBuffer(parent->buffer, GIST_EXCLUSIVE);
+		gistcheckpage(r, parent->buffer);
+		parent->page = (Page) BufferGetPage(parent->buffer);
+	}
 
-		/* ok, find new path */
-		ptr = parent = gistFindPath(r, child->blkno, &child->downlinkoffnum);
+	/*
+	 * awful!!, we need search tree to find parent ... , but before we should
+	 * release all old parent
+	 */
 
-		/* read all buffers as expected by caller */
-		/* note we don't lock them or gistcheckpage them here! */
-		while (ptr)
-		{
-			ptr->buffer = ReadBuffer(r, ptr->blkno);
-			ptr->page = (Page) BufferGetPage(ptr->buffer);
-			ptr = ptr->parent;
-		}
+	ptr = child->parent->parent;	/* child->parent already released above */
+	while (ptr)
+	{
+		ReleaseBuffer(ptr->buffer);
+		ptr = ptr->parent;
+	}
 
-		/* install new chain of parents to stack */
-		child->parent = parent;
+	/* ok, find new path */
+	ptr = parent = gistFindPath(r, child->blkno, &child->downlinkoffnum);
 
-		/* make recursive call to normal processing */
-		LockBuffer(child->parent->buffer, GIST_EXCLUSIVE);
-		gistFindCorrectParent(r, child);
+	/* read all buffers as expected by caller */
+	/* note we don't lock them or gistcheckpage them here! */
+	while (ptr)
+	{
+		ptr->buffer = ReadBuffer(r, ptr->blkno);
+		ptr->page = (Page) BufferGetPage(ptr->buffer);
+		ptr = ptr->parent;
 	}
 
-	return;
+	/* install new chain of parents to stack */
+	child->parent = parent;
+
+	/* make recursive call to normal processing */
+	LockBuffer(child->parent->buffer, GIST_EXCLUSIVE);
+	gistFindCorrectParent(r, child, is_build);
 }
 
 /*
  * Form a downlink pointer for the page in 'buf'.
  */
 static IndexTuple
 gistformdownlink(Relation rel, Buffer buf, GISTSTATE *giststate,
-				 GISTInsertStack *stack)
+				 GISTInsertStack *stack, bool is_build)
 {
 	Page		page = BufferGetPage(buf);
 	OffsetNumber maxoff;
@@ -1142,7 +1159,7 @@ gistformdownlink(Relation rel, Buffer buf, GISTSTATE *giststate,
 		ItemId		iid;
 
 		LockBuffer(stack->parent->buffer, GIST_EXCLUSIVE);
-		gistFindCorrectParent(rel, stack);
+		gistFindCorrectParent(rel, stack, is_build);
 		iid = PageGetItemId(stack->parent->page, stack->downlinkoffnum);
 		downlink = (IndexTuple) PageGetItem(stack->parent->page, iid);
 		downlink = CopyIndexTuple(downlink);
@@ -1187,7 +1204,7 @@ gistfixsplit(GISTInsertState *state, GISTSTATE *giststate)
 		page = BufferGetPage(buf);
 
 		/* Form the new downlink tuples to insert to parent */
-		downlink = gistformdownlink(state->r, buf, giststate, stack);
+		downlink = gistformdownlink(state->r, buf, giststate, stack, state->is_build);
 
 		si->buf = buf;
 		si->downlink = downlink;
@@ -1351,7 +1368,7 @@ gistfinishsplit(GISTInsertState *state, GISTInsertStack *stack,
 		right = (GISTPageSplitInfo *) linitial(reversed);
 		left = (GISTPageSplitInfo *) lsecond(reversed);
 
-		gistFindCorrectParent(state->r, stack);
+		gistFindCorrectParent(state->r, stack, state->is_build);
 		if (gistinserttuples(state, stack->parent, giststate,
 							 &right->downlink, 1,
 							 InvalidOffsetNumber,
@@ -1377,20 +1394,22 @@ gistfinishsplit(GISTInsertState *state, GISTInsertStack *stack,
 	 */
 	tuples[0] = left->downlink;
 	tuples[1] = right->downlink;
-	gistFindCorrectParent(state->r, stack);
-	if (gistinserttuples(state, stack->parent, giststate,
-						 tuples, 2,
-						 stack->downlinkoffnum,
-						 left->buf, right->buf,
-						 true,		/* Unlock parent */
-						 unlockbuf	/* Unlock stack->buffer if caller wants that */
-			))
-	{
-		/*
-		 * If the parent page was split, the downlink might have moved.
-		 */
-		stack->downlinkoffnum = InvalidOffsetNumber;
-	}
+	gistFindCorrectParent(state->r, stack, state->is_build);
+	(void) gistinserttuples(state, stack->parent, giststate,
+							tuples, 2,
+							stack->downlinkoffnum,
+							left->buf, right->buf,
+							true,	/* Unlock parent */
+							unlockbuf	/* Unlock stack->buffer if caller
+										 * wants that */
+		);
+
+	/*
+	 * The downlink might have moved when we updated it. Even if the page
+	 * wasn't split, because gistinserttuples() implements updating the old
+	 * tuple by removing and re-inserting it!
+	 */
+	stack->downlinkoffnum = InvalidOffsetNumber;
 
 	Assert(left->buf == stack->buffer);
 
