heapam: Pass number of required pages to RelationGetBufferForTuple()

anarazel · anarazel · commit 5279e9db8e8d · 2023-04-06T16:17:16.000-07:00
A future commit will use this information to determine how aggressively to extend the relation by. In heap_multi_insert() we know accurately how many pages we need once we need to extend the relation, providing an accurate lower bound for how much to extend. Reviewed-by: Melanie Plageman <melanieplageman@gmail.com> Discussion: https://postgr.es/m/20221029025420.eplyow6k7tgu6he3@awork3.anarazel.de
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
@@ -1847,7 +1847,8 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 	 */
 	buffer = RelationGetBufferForTuple(relation, heaptup->t_len,
 									   InvalidBuffer, options, bistate,
-									   &vmbuffer, NULL);
+									   &vmbuffer, NULL,
+									   0);
 
 	/*
 	 * We're about to do the actual insert -- but check for conflict first, to
@@ -2050,6 +2051,32 @@ heap_prepare_insert(Relation relation, HeapTuple tup, TransactionId xid,
 		return tup;
 }
 
+/*
+ * Helper for heap_multi_insert() that computes the number of entire pages
+ * that inserting the remaining heaptuples requires. Used to determine how
+ * much the relation needs to be extended by.
+ */
+static int
+heap_multi_insert_pages(HeapTuple *heaptuples, int done, int ntuples, Size saveFreeSpace)
+{
+	size_t		page_avail = BLCKSZ - SizeOfPageHeaderData - saveFreeSpace;
+	int			npages = 1;
+
+	for (int i = done; i < ntuples; i++)
+	{
+		size_t		tup_sz = sizeof(ItemIdData) + MAXALIGN(heaptuples[i]->t_len);
+
+		if (page_avail < tup_sz)
+		{
+			npages++;
+			page_avail = BLCKSZ - SizeOfPageHeaderData - saveFreeSpace;
+		}
+		page_avail -= tup_sz;
+	}
+
+	return npages;
+}
+
 /*
  *	heap_multi_insert	- insert multiple tuples into a heap
  *
@@ -2076,6 +2103,9 @@ heap_multi_insert(Relation relation, TupleTableSlot **slots, int ntuples,
 	Size		saveFreeSpace;
 	bool		need_tuple_data = RelationIsLogicallyLogged(relation);
 	bool		need_cids = RelationIsAccessibleInLogicalDecoding(relation);
+	bool		starting_with_empty_page = false;
+	int			npages = 0;
+	int			npages_used = 0;
 
 	/* currently not needed (thus unsupported) for heap_multi_insert() */
 	Assert(!(options & HEAP_INSERT_NO_LOGICAL));
@@ -2126,13 +2156,31 @@ heap_multi_insert(Relation relation, TupleTableSlot **slots, int ntuples,
 	while (ndone < ntuples)
 	{
 		Buffer		buffer;
-		bool		starting_with_empty_page;
 		bool		all_visible_cleared = false;
 		bool		all_frozen_set = false;
 		int			nthispage;
 
 		CHECK_FOR_INTERRUPTS();
 
+		/*
+		 * Compute number of pages needed to fit the to-be-inserted tuples in
+		 * the worst case.  This will be used to determine how much to extend
+		 * the relation by in RelationGetBufferForTuple(), if needed.  If we
+		 * filled a prior page from scratch, we can just update our last
+		 * computation, but if we started with a partially filled page,
+		 * recompute from scratch, the number of potentially required pages
+		 * can vary due to tuples needing to fit onto the page, page headers
+		 * etc.
+		 */
+		if (ndone == 0 || !starting_with_empty_page)
+		{
+			npages = heap_multi_insert_pages(heaptuples, ndone, ntuples,
+											 saveFreeSpace);
+			npages_used = 0;
+		}
+		else
+			npages_used++;
+
 		/*
 		 * Find buffer where at least the next tuple will fit.  If the page is
 		 * all-visible, this will also pin the requisite visibility map page.
@@ -2142,7 +2190,8 @@ heap_multi_insert(Relation relation, TupleTableSlot **slots, int ntuples,
 		 */
 		buffer = RelationGetBufferForTuple(relation, heaptuples[ndone]->t_len,
 										   InvalidBuffer, options, bistate,
-										   &vmbuffer, NULL);
+										   &vmbuffer, NULL,
+										   npages - npages_used);
 		page = BufferGetPage(buffer);
 
 		starting_with_empty_page = PageGetMaxOffsetNumber(page) == 0;
@@ -3576,7 +3625,8 @@ heap_update(Relation relation, ItemPointer otid, HeapTuple newtup,
 				/* It doesn't fit, must use RelationGetBufferForTuple. */
 				newbuf = RelationGetBufferForTuple(relation, heaptup->t_len,
 												   buffer, 0, NULL,
-												   &vmbuffer_new, &vmbuffer);
+												   &vmbuffer_new, &vmbuffer,
+												   0);
 				/* We're all done. */
 				break;
 			}
diff --git a/src/backend/access/heap/hio.c b/src/backend/access/heap/hio.c
@@ -301,6 +301,11 @@ RelationAddExtraBlocks(Relation relation, BulkInsertState bistate)
  *	Returns pinned and exclusive-locked buffer of a page in given relation
  *	with free space >= given len.
  *
+ *	If num_pages is > 1, we will try to extend the relation by at least that
+ *	many pages when we decide to extend the relation. This is more efficient
+ *	for callers that know they will need multiple pages
+ *	(e.g. heap_multi_insert()).
+ *
  *	If otherBuffer is not InvalidBuffer, then it references a previously
  *	pinned buffer of another page in the same relation; on return, this
  *	buffer will also be exclusive-locked.  (This case is used by heap_update;
@@ -359,7 +364,8 @@ Buffer
 RelationGetBufferForTuple(Relation relation, Size len,
 						  Buffer otherBuffer, int options,
 						  BulkInsertState bistate,
-						  Buffer *vmbuffer, Buffer *vmbuffer_other)
+						  Buffer *vmbuffer, Buffer *vmbuffer_other,
+						  int num_pages)
 {
 	bool		use_fsm = !(options & HEAP_INSERT_SKIP_FSM);
 	Buffer		buffer = InvalidBuffer;
diff --git a/src/include/access/hio.h b/src/include/access/hio.h
@@ -38,6 +38,7 @@ extern void RelationPutHeapTuple(Relation relation, Buffer buffer,
 extern Buffer RelationGetBufferForTuple(Relation relation, Size len,
 										Buffer otherBuffer, int options,
 										BulkInsertStateData *bistate,
-										Buffer *vmbuffer, Buffer *vmbuffer_other);
+										Buffer *vmbuffer, Buffer *vmbuffer_other,
+										int num_pages);
 
 #endif							/* HIO_H */
