agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v1] bufmgr: aio: Prototype for not waiting for already-in-progress IO
9610+ messages / 2 participants
[nested] [flat]

* [PATCH v1] bufmgr: aio: Prototype for not waiting for already-in-progress IO
@ 2025-08-15 15:01  Andres Freund <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Andres Freund @ 2025-08-15 15:01 UTC (permalink / raw)

Author:
Reviewed-by:
Discussion: https://postgr.es/m/
Backpatch:
---
 src/include/storage/bufmgr.h        |   1 +
 src/backend/storage/buffer/bufmgr.c | 133 ++++++++++++++++++++++++++--
 2 files changed, 125 insertions(+), 9 deletions(-)

diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 41fdc1e7693..7ddb867bc99 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -137,6 +137,7 @@ struct ReadBuffersOperation
 	int			flags;
 	int16		nblocks;
 	int16		nblocks_done;
+	bool		foreign_io;
 	PgAioWaitRef io_wref;
 	PgAioReturn io_return;
 };
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index fd7e21d96d3..de755fd53ad 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -1557,6 +1557,41 @@ ReadBuffersCanStartIOOnce(Buffer buffer, bool nowait)
 		return StartBufferIO(GetBufferDescriptor(buffer - 1), true, nowait);
 }
 
+static inline bool
+ReadBuffersIOAlreadyInProgress(ReadBuffersOperation *operation, Buffer buffer)
+{
+	BufferDesc *desc;
+	uint32		buf_state;
+	PgAioWaitRef iow;
+
+	pgaio_wref_clear(&iow);
+
+	if (BufferIsLocal(buffer))
+	{
+		desc = GetLocalBufferDescriptor(-buffer - 1);
+		buf_state = pg_atomic_read_u32(&desc->state);
+		if (buf_state & BM_IO_IN_PROGRESS)
+			iow = desc->io_wref;
+	}
+	else
+	{
+		desc = GetBufferDescriptor(buffer - 1);
+		buf_state = LockBufHdr(desc);
+
+		if (buf_state & BM_IO_IN_PROGRESS)
+			iow = desc->io_wref;
+		UnlockBufHdr(desc, buf_state);
+	}
+
+	if (pgaio_wref_valid(&iow))
+	{
+		operation->io_wref = iow;
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Helper for AsyncReadBuffers that tries to get the buffer ready for IO.
  */
@@ -1689,7 +1724,7 @@ WaitReadBuffers(ReadBuffersOperation *operation)
 			 *
 			 * we first check if we already know the IO is complete.
 			 */
-			if (aio_ret->result.status == PGAIO_RS_UNKNOWN &&
+			if ((operation->foreign_io || aio_ret->result.status == PGAIO_RS_UNKNOWN) &&
 				!pgaio_wref_check_done(&operation->io_wref))
 			{
 				instr_time	io_start = pgstat_prepare_io_time(track_io_timing);
@@ -1708,11 +1743,38 @@ WaitReadBuffers(ReadBuffersOperation *operation)
 				Assert(pgaio_wref_check_done(&operation->io_wref));
 			}
 
-			/*
-			 * We now are sure the IO completed. Check the results. This
-			 * includes reporting on errors if there were any.
-			 */
-			ProcessReadBuffersResult(operation);
+			if (operation->foreign_io)
+			{
+				Buffer		buffer = operation->buffers[operation->nblocks_done];
+				BufferDesc *desc;
+				uint32		buf_state;
+
+				if (BufferIsLocal(buffer))
+				{
+					desc = GetLocalBufferDescriptor(-buffer - 1);
+					buf_state = pg_atomic_read_u32(&desc->state);
+				}
+				else
+				{
+					desc = GetBufferDescriptor(buffer - 1);
+					buf_state = LockBufHdr(desc);
+					UnlockBufHdr(desc, buf_state);
+				}
+
+				if (buf_state & BM_VALID)
+				{
+					operation->nblocks_done += 1;
+					Assert(operation->nblocks_done <= operation->nblocks);
+				}
+			}
+			else
+			{
+				/*
+				 * We now are sure the IO completed. Check the results. This
+				 * includes reporting on errors if there were any.
+				 */
+				ProcessReadBuffersResult(operation);
+			}
 		}
 
 		/*
@@ -1798,6 +1860,56 @@ AsyncReadBuffers(ReadBuffersOperation *operation, int *nblocks_progress)
 		io_object = IOOBJECT_RELATION;
 	}
 
+	/*
+	 * If AIO is in progress, be it in this backend or another backend, we
+	 * just associate the wait reference with the operation and wait in
+	 * WaitReadBuffers(). This turns out to be important for performance in
+	 * two workloads:
+	 *
+	 * 1) A read stream that has to read the same block multiple times within
+	 *	  the readahead distance. This can happen e.g. for the table accesses
+	 *	  of an index scan.
+	 *
+	 * 2) Concurrent scans by multiple backends on the same relation.
+	 *
+	 * If we were to synchronously wait for the in-progress IO, we'd not be
+	 * able to keep enough I/O in flight.
+	 *
+	 *
+	 * If we do find there is ongoing I/O for the buffer, we set up a 1-block
+	 * ReadBuffersOperation that WaitReadBuffers then can wait on.
+	 */
+	if (1 && ReadBuffersIOAlreadyInProgress(operation, buffers[nblocks_done]))
+	{
+		/* FIXME: probably need to wait if io_method == sync? */
+
+		*nblocks_progress = 1;
+		did_start_io = true;
+		operation->foreign_io = true;
+
+		if (0)
+			elog(LOG, "using foreign IO path");
+
+		/* FIXME: trace point */
+
+		/*
+		 * FIXME: how should this be accounted for in stats? Account as a hit
+		 * for now, quite likely *we* started this IO.
+		 */
+		if (persistence == RELPERSISTENCE_TEMP)
+			pgBufferUsage.local_blks_hit += 1;
+		else
+			pgBufferUsage.shared_blks_hit += 1;
+
+		if (operation->rel)
+			pgstat_count_buffer_hit(operation->rel);
+		pgstat_count_io_op(io_object, io_context, IOOP_HIT, 1, 0);
+		if (VacuumCostActive)
+			VacuumCostBalance += VacuumCostPageHit;
+
+		return true;
+	}
+
 	/*
 	 * If zero_damaged_pages is enabled, add the READ_BUFFERS_ZERO_ON_ERROR
 	 * flag. The reason for that is that, hopefully, zero_damaged_pages isn't
@@ -1855,9 +1967,9 @@ AsyncReadBuffers(ReadBuffersOperation *operation, int *nblocks_progress)
 	/*
 	 * Check if we can start IO on the first to-be-read buffer.
 	 *
-	 * If an I/O is already in progress in another backend, we want to wait
-	 * for the outcome: either done, or something went wrong and we will
-	 * retry.
+	 * If a synchronous I/O in progress in another backend (it can't be this
+	 * backend), we want to wait for the outcome: either done, or something
+	 * went wrong and we will retry.
 	 */
 	if (!ReadBuffersCanStartIO(buffers[nblocks_done], false))
 	{
@@ -1970,6 +2082,7 @@ AsyncReadBuffers(ReadBuffersOperation *operation, int *nblocks_progress)
 		if (VacuumCostActive)
 			VacuumCostBalance += VacuumCostPageMiss * io_buffers_len;
 
+		operation->foreign_io = false;
 		*nblocks_progress = io_buffers_len;
 		did_start_io = true;
 	}
@@ -5986,6 +6099,8 @@ WaitIO(BufferDesc *buf)
 		 */
 		if (pgaio_wref_valid(&iow))
 		{
+			if (0)
+				elog(LOG, "foreign wait");
 			pgaio_wref_wait(&iow);
 
 			/*
-- 
2.48.1.76.g4e746b1a31.dirty


--j4imdtjxqt5tb6mo--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9610+ messages in thread

From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw)

It should make the copying more efficient. Besides that, buffer access
strategy is involved this way.

This diff reverts the changes done in previous parts of the series to
reform_and_rewrite_tuple() and introduces a separate function
heap_insert_for_repack().
---
 src/backend/access/heap/heapam_handler.c | 110 +++++++++++++++--------
 1 file changed, 72 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index f4c62e5bc7a..50ddee9d8c8 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -49,6 +49,11 @@
 static void reform_and_rewrite_tuple(HeapTuple tuple,
 									 Relation OldHeap, Relation NewHeap,
 									 Datum *values, bool *isnull, RewriteState rwstate);
+static void heap_insert_for_repack(HeapTuple tuple, Relation OldHeap,
+								   Relation NewHeap, Datum *values, bool *isnull,
+								   BulkInsertState bistate);
+static HeapTuple reform_tuple(HeapTuple tuple, Relation OldHeap,
+							  Relation NewHeap, Datum *values, bool *isnull);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -694,6 +699,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 								 double *tups_recently_dead)
 {
 	RewriteState rwstate = NULL;
+	BulkInsertState	bistate = NULL;
 	IndexScanDesc indexScan;
 	TableScanDesc tableScan;
 	HeapScanDesc heapScan;
@@ -729,6 +735,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	if (!concurrent)
 		rwstate = begin_heap_rewrite(OldHeap, NewHeap, OldestXmin,
 									 *xid_cutoff, *multi_cutoff);
+	else
+		bistate = GetBulkInsertState();
 
 
 	/* Set up sorting if wanted */
@@ -958,8 +966,12 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			};
 			int64		ct_val[2];
 
-			reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-									 values, isnull, rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
+										 values, isnull, rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -1007,10 +1019,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 				break;
 
 			n_tuples += 1;
-			reform_and_rewrite_tuple(tuple,
-									 OldHeap, NewHeap,
-									 values, isnull,
-									 rwstate);
+			if (!concurrent)
+				reform_and_rewrite_tuple(tuple,
+										 OldHeap, NewHeap,
+										 values, isnull,
+										 rwstate);
+			else
+				heap_insert_for_repack(tuple, OldHeap, NewHeap,
+									   values, isnull, bistate);
+
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
@@ -1022,6 +1039,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
+	if (bistate)
+		FreeBulkInsertState(bistate);
 
 	/* Clean up */
 	pfree(values);
@@ -2414,56 +2433,71 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * SET WITHOUT OIDS.
  *
  * So, we must reconstruct the tuple from component Datums.
- *
- * If rwstate=NULL, use simple_heap_insert() instead of rewriting - in that
- * case we still need to deform/form the tuple. TODO Shouldn't we rename the
- * function, as might not do any rewrite?
  */
 static void
 reform_and_rewrite_tuple(HeapTuple tuple,
 						 Relation OldHeap, Relation NewHeap,
 						 Datum *values, bool *isnull, RewriteState rwstate)
+{
+	HeapTuple       copiedTuple;
+
+	copiedTuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	/* The heap rewrite module does the rest */
+	rewrite_heap_tuple(rwstate, tuple, copiedTuple);
+
+	heap_freetuple(copiedTuple);
+}
+
+/*
+ * Insert tuple when processing REPACK CONCURRENTLY.
+ *
+ * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
+ * difficult to do the same in the catch-up phase (as the logical
+ * decoding does not provide us with sufficient visibility
+ * information). Thus we must use heap_insert() both during the
+ * catch-up and here.
+ *
+ * We pass the NO_LOGICAL flag to heap_insert() in order to skip logical
+ * decoding: as soon as REPACK CONCURRENTLY swaps the relation files, it drops
+ * this relation, so no logical replication subscription should need the data.
+ *
+ * BulkInsertState is used because many tuples are inserted in the typical
+ * case.
+ */
+static void
+heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+					   Datum *values, bool *isnull, BulkInsertState bistate)
+{
+	tuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+
+	heap_insert(NewHeap, tuple, GetCurrentCommandId(true),
+				HEAP_INSERT_NO_LOGICAL, bistate);
+
+	heap_freetuple(tuple);
+}
+
+/*
+ * Deform tuple, set values of dropped columns to NULL, form a new tuple and
+ * return it.
+ */
+static HeapTuple
+reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
+			 Datum *values, bool *isnull)
 {
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
 	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	HeapTuple	copiedTuple;
 	int			i;
 
 	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
 
-	/* Be sure to null out any dropped columns */
 	for (i = 0; i < newTupDesc->natts; i++)
 	{
 		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
 			isnull[i] = true;
 	}
 
-	copiedTuple = heap_form_tuple(newTupDesc, values, isnull);
-
-	if (rwstate)
-		/* The heap rewrite module does the rest */
-		rewrite_heap_tuple(rwstate, tuple, copiedTuple);
-	else
-	{
-		/*
-		 * Insert tuple when processing REPACK CONCURRENTLY.
-		 *
-		 * rewriteheap.c is not used in the CONCURRENTLY case because it'd be
-		 * difficult to do the same in the catch-up phase (as the logical
-		 * decoding does not provide us with sufficient visibility
-		 * information). Thus we must use heap_insert() both during the
-		 * catch-up and here.
-		 *
-		 * The following is like simple_heap_insert() except that we pass the
-		 * flag to skip logical decoding: as soon as REPACK CONCURRENTLY swaps
-		 * the relation files, it drops this relation, so no logical
-		 * replication subscription should need the data.
-		 */
-		heap_insert(NewHeap, copiedTuple, GetCurrentCommandId(true),
-					HEAP_INSERT_NO_LOGICAL, NULL);
-	}
-
-	heap_freetuple(copiedTuple);
+	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9610+ messages in thread