From 40bcb601af134bfa13af29baecf5d6a6f299e5d7 Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplageman@gmail.com>
Date: Tue, 29 Jul 2025 16:12:56 -0400
Subject: [PATCH v6 20/20] Set pd_prune_xid on insert

Now that we can set the VM during read-only queries, it makes sense to
start setting the page prunable hint on insert. This will allow
heap_page_prune_and_freeze() to be called when the page is full or
mostly full.

For years there has been a note in heap_insert() and heap_multi_insert()
pointing out that setting pd_prune_xid would help clean up aborted
inserted tuples that would otherwise not be cleaned up until vacuum.
So, that's another benefit of setting it.
---
 src/backend/access/heap/heapam.c      | 25 +++++++++++++++++--------
 src/backend/access/heap/heapam_xlog.c | 15 ++++++++++++++-
 2 files changed, 31 insertions(+), 9 deletions(-)

diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index f90b014a9b0..e0f2245052c 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -2094,6 +2094,7 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 	TransactionId xid = GetCurrentTransactionId();
 	HeapTuple	heaptup;
 	Buffer		buffer;
+	Page		page;
 	Buffer		vmbuffer = InvalidBuffer;
 	bool		all_visible_cleared = false;
 
@@ -2153,15 +2154,19 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 	}
 
 	/*
-	 * XXX Should we set PageSetPrunable on this page ?
+	 * Set pd_prune_xid to trigger heap_page_prune_and_freeze() once the page
+	 * is full so that we can set the page all-visible in the VM.
 	 *
-	 * The inserting transaction may eventually abort thus making this tuple
-	 * DEAD and hence available for pruning. Though we don't want to optimize
-	 * for aborts, if no other tuple in this page is UPDATEd/DELETEd, the
-	 * aborted tuple will never be pruned until next vacuum is triggered.
+	 * Setting pd_prune_xid is also handy if the inserting transaction
+	 * eventually aborts making this tuple DEAD and hence available for
+	 * pruning. If no other tuple in this page is UPDATEd/DELETEd, the aborted
+	 * tuple would never otherwise be pruned until next vacuum is triggered.
 	 *
-	 * If you do add PageSetPrunable here, add it in heap_xlog_insert too.
+	 * Don't set it if we are in bootstrap mode, though.
 	 */
+	page = BufferGetPage(buffer);
+	if (TransactionIdIsNormal(xid))
+		PageSetPrunable(page, xid);
 
 	MarkBufferDirty(buffer);
 
@@ -2171,7 +2176,6 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
 		xl_heap_insert xlrec;
 		xl_heap_header xlhdr;
 		XLogRecPtr	recptr;
-		Page		page = BufferGetPage(buffer);
 		uint8		info = XLOG_HEAP_INSERT;
 		int			bufflags = 0;
 
@@ -2534,8 +2538,13 @@ heap_multi_insert(Relation relation, TupleTableSlot **slots, int ntuples,
 		}
 
 		/*
-		 * XXX Should we set PageSetPrunable on this page ? See heap_insert()
+		 * Set pd_prune_xid. See heap_insert() for more on why we do this when
+		 * inserting tuples. This only makes sense if we aren't already
+		 * setting the page frozen in the VM. We also don't set it in
+		 * bootstrap mode.
 		 */
+		if (!all_frozen_set && TransactionIdIsNormal(xid))
+			PageSetPrunable(page, xid);
 
 		MarkBufferDirty(buffer);
 
diff --git a/src/backend/access/heap/heapam_xlog.c b/src/backend/access/heap/heapam_xlog.c
index 64f06d46bf1..234e9a401b9 100644
--- a/src/backend/access/heap/heapam_xlog.c
+++ b/src/backend/access/heap/heapam_xlog.c
@@ -473,6 +473,12 @@ heap_xlog_insert(XLogReaderState *record)
 
 		freespace = PageGetHeapFreeSpace(page); /* needed to update FSM below */
 
+		/*
+		 * Set the page prunable to trigger on-access pruning later which may
+		 * set the page all-visible in the VM.
+		 */
+		PageSetPrunable(page, XLogRecGetXid(record));
+
 		PageSetLSN(page, lsn);
 
 		if (xlrec->flags & XLH_INSERT_ALL_VISIBLE_CLEARED)
@@ -622,9 +628,16 @@ heap_xlog_multi_insert(XLogReaderState *record)
 		if (xlrec->flags & XLH_INSERT_ALL_VISIBLE_CLEARED)
 			PageClearAllVisible(page);
 
-		/* XLH_INSERT_ALL_FROZEN_SET implies that all tuples are visible */
+		/*
+		 * XLH_INSERT_ALL_FROZEN_SET implies that all tuples are visible. If
+		 * we are not setting the page frozen, then set the page's prunable
+		 * hint so that we trigger on-access pruning later which may set the
+		 * page all-visible in the VM.
+		 */
 		if (xlrec->flags & XLH_INSERT_ALL_FROZEN_SET)
 			PageSetAllVisible(page);
+		else
+			PageSetPrunable(page, XLogRecGetXid(record));
 
 		MarkBufferDirty(buffer);
 	}
-- 
2.43.0

