Truncate line pointer array during heap pruning.

Reclaim space from the line pointer array when heap pruning leaves
behind a contiguous group of LP_UNUSED items at the end of the array.
This happens during subsequent page defragmentation.  Certain kinds of
heap line pointer bloat are ameliorated by this new optimization.

Follow-up work to commit 3c3b8a4b26, which taught VACUUM to truncate the
line pointer array in about the same way during VACUUM's second pass
over the heap.  We now apply line pointer array truncation during both
the first and the second pass over the heap made by VACUUM.  We can also
perform line pointer array truncation during opportunistic pruning.

Matthias van de Meent, with small tweaks by me.

Author: Matthias van de Meent <boekewurm+postgres@gmail.com>
Discussion: https://postgr.es/m/CAEze2WjgaQc55Y5f5CQd3L=eS5CZcff2Obxp=O6pto8-f0hC4w@mail.gmail.com
Discussion: https://postgr.es/m/CAEze2Wg36%2B4at2eWJNcYNiW2FJmht34x3YeX54ctUSs7kKoNcA%40mail.gmail.com

3 files changed, 33 insertions, 17 deletions

diff --git a/src/backend/access/heap/pruneheap.c b/src/backend/access/heap/pruneheap.c
index 4656f1b3db4..98d31de0031 100644
--- a/src/backend/access/heap/pruneheap.c
+++ b/src/backend/access/heap/pruneheap.c
@@ -244,7 +244,9 @@ heap_page_prune_opt(Relation relation, Buffer buffer)
  * Prune and repair fragmentation in the specified page.
  *
  * Caller must have pin and buffer cleanup lock on the page.  Note that we
- * don't update the FSM information for page on caller's behalf.
+ * don't update the FSM information for page on caller's behalf.  Caller might
+ * also need to account for a reduction in the length of the line pointer
+ * array following array truncation by us.
  *
  * vistest is used to distinguish whether tuples are DEAD or RECENTLY_DEAD
  * (see heap_prune_satisfies_vacuum and
diff --git a/src/backend/access/heap/vacuumlazy.c b/src/backend/access/heap/vacuumlazy.c
index 092b739dda9..e1cac74e620 100644
--- a/src/backend/access/heap/vacuumlazy.c
+++ b/src/backend/access/heap/vacuumlazy.c
@@ -223,7 +223,7 @@ typedef struct LVRelState
  */
 typedef struct LVPagePruneState
 {
-	bool		hastup;			/* Page is truncatable? */
+	bool		hastup;			/* Page prevents rel truncation? */
 	bool		has_lpdead_items;	/* includes existing LP_DEAD items */
 
 	/*
@@ -1393,7 +1393,7 @@ lazy_scan_skip(LVRelState *vacrel, Buffer *vmbuffer, BlockNumber next_block,
  *
  * It's necessary to consider new pages as a special case, since the rules for
  * maintaining the visibility map and FSM with empty pages are a little
- * different (though new pages can be truncated based on the usual rules).
+ * different (though new pages can be truncated away during rel truncation).
  *
  * Empty pages are not really a special case -- they're just heap pages that
  * have no allocated tuples (including even LP_UNUSED items).  You might
@@ -1561,6 +1561,11 @@ lazy_scan_prune(LVRelState *vacrel,
 
 	Assert(BufferGetBlockNumber(buf) == blkno);
 
+	/*
+	 * maxoff might be reduced following line pointer array truncation in
+	 * heap_page_prune.  That's safe for us to ignore, since the reclaimed
+	 * space will continue to look like LP_UNUSED items below.
+	 */
 	maxoff = PageGetMaxOffsetNumber(page);
 
 retry:
@@ -1768,7 +1773,7 @@ retry:
 		 * Check tuple left behind after pruning to see if needs to be frozen
 		 * now.
 		 */
-		prunestate->hastup = true;	/* page won't be truncatable */
+		prunestate->hastup = true;	/* page makes rel truncation unsafe */
 		if (heap_prepare_freeze_tuple(tuple.t_data,
 									  vacrel->relfrozenxid,
 									  vacrel->relminmxid,
diff --git a/src/backend/storage/page/bufpage.c b/src/backend/storage/page/bufpage.c
index 147ba4d9232..366d57ea7ac 100644
--- a/src/backend/storage/page/bufpage.c
+++ b/src/backend/storage/page/bufpage.c
@@ -688,22 +688,14 @@ compactify_tuples(itemIdCompact itemidbase, int nitems, Page page, bool presorte
  *
  * This routine is usable for heap pages only, but see PageIndexMultiDelete.
  *
- * Never removes unused line pointers.  PageTruncateLinePointerArray can
- * safely remove some unused line pointers.  It ought to be safe for this
- * routine to free unused line pointers in roughly the same way, but it's not
- * clear that that would be beneficial.
- *
- * PageTruncateLinePointerArray is only called during VACUUM's second pass
- * over the heap.  Any unused line pointers that it sees are likely to have
- * been set to LP_UNUSED (from LP_DEAD) immediately before the time it is
- * called.  On the other hand, many tables have the vast majority of all
- * required pruning performed opportunistically (not during VACUUM).  And so
- * there is, in general, a good chance that even large groups of unused line
- * pointers that we see here will be recycled quickly.
+ * This routine removes unused line pointers from the end of the line pointer
+ * array.  This is possible when dead heap-only tuples get removed by pruning,
+ * especially when there were HOT chains with several tuples each beforehand.
  *
  * Caller had better have a full cleanup lock on page's buffer.  As a side
  * effect the page's PD_HAS_FREE_LINES hint bit will be set or unset as
- * needed.
+ * needed.  Caller might also need to account for a reduction in the length of
+ * the line pointer array following array truncation.
  */
 void
 PageRepairFragmentation(Page page)
@@ -718,6 +710,7 @@ PageRepairFragmentation(Page page)
 	int			nline,
 				nstorage,
 				nunused;
+	OffsetNumber finalusedlp = InvalidOffsetNumber;
 	int			i;
 	Size		totallen;
 	bool		presorted = true;	/* For now */
@@ -771,10 +764,13 @@ PageRepairFragmentation(Page page)
 				totallen += itemidptr->alignedlen;
 				itemidptr++;
 			}
+
+			finalusedlp = i;	/* Could be the final non-LP_UNUSED item */
 		}
 		else
 		{
 			/* Unused entries should have lp_len = 0, but make sure */
+			Assert(!ItemIdHasStorage(lp));
 			ItemIdSetUnused(lp);
 			nunused++;
 		}
@@ -798,6 +794,19 @@ PageRepairFragmentation(Page page)
 		compactify_tuples(itemidbase, nstorage, page, presorted);
 	}
 
+	if (finalusedlp != nline)
+	{
+		/* The last line pointer is not the last used line pointer */
+		int		nunusedend = nline - finalusedlp;
+
+		Assert(nunused >= nunusedend && nunusedend > 0);
+
+		/* remove trailing unused line pointers from the count */
+		nunused -= nunusedend;
+		/* truncate the line pointer array */
+		((PageHeader) page)->pd_lower -= (sizeof(ItemIdData) * nunusedend);
+	}
+
 	/* Set hint bit for PageAddItemExtended */
 	if (nunused > 0)
 		PageSetHasFreeLinePointers(page);