Truncate line pointer array during VACUUM.

Teach VACUUM to truncate the line pointer array of each heap page when a
contiguous group of LP_UNUSED line pointers appear at the end of the
array -- these unused and unreferenced items are excluded.  This process
occurs during VACUUM's second pass over the heap, right after LP_DEAD
line pointers on the page (those encountered/pruned during the first
pass) are marked LP_UNUSED.

Truncation avoids line pointer bloat with certain workloads,
particularly those involving continual range DELETEs and bulk INSERTs
against the same table.

Also harden heapam code to check for an out-of-range page offset number
in places where we weren't already doing so.

Author: Matthias van de Meent <boekewurm+postgres@gmail.com>
Author: Peter Geoghegan <pg@bowt.ie>
Reviewed-By: Masahiko Sawada <sawada.mshk@gmail.com>
Reviewed-By: Peter Geoghegan <pg@bowt.ie>
Discussion: https://postgr.es/m/CAEze2WjgaQc55Y5f5CQd3L=eS5CZcff2Obxp=O6pto8-f0hC4w@mail.gmail.com
Discussion: https://postgr.es/m/CAH2-Wzn6a64PJM1Ggzm=uvx2otsopJMhFQj_g1rAj4GWr3ZSzw@mail.gmail.com

src/backend/access/heap/heapam.c

@@ -635,8 +635,15 @@ heapgettup(HeapScanDesc scan,
 		}
 		else
 		{
+			/*
+			 * The previous returned tuple may have been vacuumed since the
+			 * previous scan when we use a non-MVCC snapshot, so we must
+			 * re-establish the lineoff <= PageGetMaxOffsetNumber(dp)
+			 * invariant
+			 */
 			lineoff =			/* previous offnum */
-				OffsetNumberPrev(ItemPointerGetOffsetNumber(&(tuple->t_self)));
+				Min(lines,
+					OffsetNumberPrev(ItemPointerGetOffsetNumber(&(tuple->t_self))));
 		}
 		/* page and lineoff now reference the physically previous tid */
 
@@ -678,6 +685,13 @@ heapgettup(HeapScanDesc scan,
 	lpp = PageGetItemId(dp, lineoff);
 	for (;;)
 	{
+		/*
+		 * Only continue scanning the page while we have lines left.
+		 *
+		 * Note that this protects us from accessing line pointers past
+		 * PageGetMaxOffsetNumber(); both for forward scans when we resume the
+		 * table scan, and for when we start scanning a new page.
+		 */
 		while (linesleft > 0)
 		{
 			if (ItemIdIsNormal(lpp))
@@ -8556,10 +8570,8 @@ heap_xlog_vacuum(XLogReaderState *record)
 			ItemIdSetUnused(lp);
 		}
 
-		/*
-		 * Update the page's hint bit about whether it has free pointers
-		 */
-		PageSetHasFreeLinePointers(page);
+		/* Attempt to truncate line pointer array now */
+		PageTruncateLinePointerArray(page);
 
 		PageSetLSN(page, lsn);
 		MarkBufferDirty(buffer);

src/backend/access/heap/pruneheap.c

@@ -962,6 +962,10 @@ heap_get_root_tuples(Page page, OffsetNumber *root_offsets)
 		 */
 		for (;;)
 		{
+			/* Sanity check */
+			if (nextoffnum < FirstOffsetNumber || nextoffnum > maxoff)
+				break;
+
 			lp = PageGetItemId(page, nextoffnum);
 
 			/* Check for broken chains */

src/backend/access/heap/vacuumlazy.c

@@ -1444,7 +1444,11 @@ lazy_scan_heap(LVRelState *vacrel, VacuumParams *params, bool aggressive)
 		if (prunestate.has_lpdead_items && vacrel->do_index_vacuuming)
 		{
 			/*
-			 * Wait until lazy_vacuum_heap_rel() to save free space.
+			 * Wait until lazy_vacuum_heap_rel() to save free space.  This
+			 * doesn't just save us some cycles; it also allows us to record
+			 * any additional free space that lazy_vacuum_heap_page() will
+			 * make available in cases where it's possible to truncate the
+			 * page's line pointer array.
 			 *
 			 * Note: The one-pass (no indexes) case is only supposed to make
 			 * it this far when there were no LP_DEAD items during pruning.
@@ -2033,6 +2037,13 @@ lazy_vacuum_all_indexes(LVRelState *vacrel)
  * Pages that never had lazy_scan_prune record LP_DEAD items are not visited
  * at all.
  *
+ * We may also be able to truncate the line pointer array of the heap pages we
+ * visit.  If there is a contiguous group of LP_UNUSED items at the end of the
+ * array, it can be reclaimed as free space.  These LP_UNUSED items usually
+ * start out as LP_DEAD items recorded by lazy_scan_prune (we set items from
+ * each page to LP_UNUSED, and then consider if it's possible to truncate the
+ * page's line pointer array).
+ *
  * Note: the reason for doing this as a second pass is we cannot remove the
  * tuples until we've removed their index entries, and we want to process
  * index entry removal in batches as large as possible.
@@ -2175,7 +2186,8 @@ lazy_vacuum_heap_page(LVRelState *vacrel, BlockNumber blkno, Buffer buffer,
 
 	Assert(uncnt > 0);
 
-	PageSetHasFreeLinePointers(page);
+	/* Attempt to truncate line pointer array now */
+	PageTruncateLinePointerArray(page);
 
 	/*
 	 * Mark buffer dirty before we write WAL.