agora inbox for pgsql-hackers@postgresql.org  

help / color / mirror / Atom feed

[PATCH 5/5] Serialize decoded tuples without flattening.
382+ messages / 2 participants
[nested] [flat]

* [PATCH 5/5] Serialize decoded tuples without flattening.
@ 2026-02-27 18:01 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 382+ messages in thread

From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw)

So far we used to flatten the tuples produced by logical decoding in order to
write them to a temporary file. That means that all the TOASTed attributes
ended up in a single chunk of memory. The problem is that even if individual
attributes do fit into the maximum chunk size (currently 1 GB), the whole
tuple is not guaranteed to fit.

The flattening might be a problem in the future anyway, since there's an
effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin
horizon. However, as the flattening assumes scans of the TOAST relaation, the
less we restrict VACUUM, the more likely it is that the TOAST attributes
needed for the flattening won't be available at decoding time.

(This patch also removes unnecessary field 'tupdesc' from RepackDecodingState
and allocates it in the appropriate memory context.)
---
 src/backend/commands/cluster.c                | 260 +++++++++++++++---
 .../pgoutput_repack/pgoutput_repack.c         | 114 ++++++--
 src/include/commands/cluster.h                |   5 +-
 .../expected/repack_toast.out                 |   1 +
 .../injection_points/specs/repack_toast.spec  |   7 +
 5 files changed, 318 insertions(+), 69 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index db710259eeb..e4de410e733 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -35,6 +35,7 @@
 #include "postgres.h"
 
 #include "access/amapi.h"
+#include "access/detoast.h"
 #include "access/heapam.h"
 #include "access/multixact.h"
 #include "access/relscan.h"
@@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup,
 									IndexInsertState *iistate,
 									TupleTableSlot *index_slot);
 static void apply_concurrent_delete(Relation rel, HeapTuple tup_target);
+static HeapTuple restore_tuple(BufFile *file, Relation relation,
+							   MemoryContext cxt);
+static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst,
+									   HeapTuple tup_src, MemoryContext cxt);
 static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest,
 								   HeapTuple tup_key,
 								   TupleTableSlot *ident_slot);
@@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid)
 	LogicalDecodingContext *ctx;
 	NameData	slotname;
 	RepackDecodingState *dstate;
+	MemoryContext oldcxt;
 
 	/*
 	 * REPACK CONCURRENTLY is not allowed in a transaction block, so this
@@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid)
 	 */
 	ctx->reader->routine.page_read = read_local_xlog_page_no_wait;
 
-	/*
-	 * read_local_xlog_page_no_wait() needs to be able to indicate the end of
-	 * WAL.
-	 */
-	ctx->reader->private_data = MemoryContextAllocZero(ctx->context,
-													   sizeof(ReadLocalXLogPageNoWaitPrivate));
-
-
 	/* Some WAL records should have been read. */
 	Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr);
 
@@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid)
 	XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment,
 				wal_segment_size);
 
-	dstate = palloc0_object(RepackDecodingState);
-	dstate->relid = relid;
+	/* Our private state belongs to the decoding context. */
+	oldcxt = MemoryContextSwitchTo(ctx->context);
 
 	/*
-	 * Tuple descriptor may be needed to flatten a tuple before we write it to
-	 * a file. A copy is needed because the decoding worker invalidates system
-	 * caches before it starts to do the actual work.
+	 * read_local_xlog_page_no_wait() needs to be able to indicate the end of
+	 * WAL.
 	 */
-	rel = table_open(relid, AccessShareLock);
-	dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel));
+	ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate);
+	dstate = palloc0_object(RepackDecodingState);
+	MemoryContextSwitchTo(oldcxt);
+
+#ifdef	USE_ASSERT_CHECKING
+	dstate->relid = relid;
+#endif
 
 	/* Avoid logical decoding of other relations. */
+	rel = table_open(relid, AccessShareLock);
 	repacked_rel_locator = rel->rd_locator;
 	toastrelid = rel->rd_rel->reltoastrelid;
 	if (OidIsValid(toastrelid))
@@ -2822,10 +2825,10 @@ static void
 apply_concurrent_changes(BufFile *file, ChangeDest *dest)
 {
 	char		kind;
-	uint32		t_len;
 	Relation	rel = dest->rel;
 	TupleTableSlot *index_slot,
 			   *ident_slot;
+	MemoryContext apply_cxt;
 	HeapTuple	tup_old = NULL;
 
 	/* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */
@@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
 	/* A slot to fetch tuples from identity index. */
 	ident_slot = table_slot_create(rel, NULL);
 
+	/*
+	 * Use a separate memory context for the tuples and any memory needed to
+	 * process them.
+	 */
+	apply_cxt = AllocSetContextCreate(TopTransactionContext,
+									  "REPACK - apply",
+									  ALLOCSET_DEFAULT_SIZES);
+
 	while (true)
 	{
 		size_t		nread;
@@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
 			break;
 
 		/* Read the tuple. */
-		BufFileReadExact(file, &t_len, sizeof(t_len));
-		tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len);
-		tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE);
-		BufFileReadExact(file, tup->t_data, t_len);
-		tup->t_len = t_len;
-		ItemPointerSetInvalid(&tup->t_self);
-		tup->t_tableOid = RelationGetRelid(dest->rel);
-
+		tup = restore_tuple(file, rel, apply_cxt);
 		if (kind == CHANGE_UPDATE_OLD)
 		{
 			Assert(tup_old == NULL);
@@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
 
 			apply_concurrent_insert(rel, tup, dest->iistate, index_slot);
 
-			pfree(tup);
+			MemoryContextReset(apply_cxt);
 		}
 		else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE)
 		{
@@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
 				elog(ERROR, "failed to find target tuple");
 
 			if (kind == CHANGE_UPDATE_NEW)
+			{
+				/*
+				 * If 'tup' contains TOAST pointers, they point to the old
+				 * relation's toast. Copy the corresponding TOAST pointers for
+				 * the new relation from the existing tuple. (The fact that we
+				 * received a TOAST pointer here implies that the attribute
+				 * hasn't changed.)
+				 */
+				if (HeapTupleHasExternal(tup))
+					tup = adjust_toast_pointers(rel, tup, tup_exist,
+												apply_cxt);
+
 				apply_concurrent_update(rel, tup, tup_exist, dest->iistate,
 										index_slot);
+			}
 			else
 				apply_concurrent_delete(rel, tup_exist);
 
 			if (tup_old != NULL)
-			{
-				pfree(tup_old);
 				tup_old = NULL;
-			}
 
-			pfree(tup);
+			MemoryContextReset(apply_cxt);
 		}
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
@@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest)
 	}
 
 	/* Cleanup. */
+	MemoryContextDelete(apply_cxt);
 	ExecDropSingleTupleTableSlot(index_slot);
 	ExecDropSingleTupleTableSlot(ident_slot);
 }
@@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target)
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1);
 }
 
+/*
+ * Read tuple from file and store it in given memory context.
+ *
+ * External attributes are stored in separate memory chunks, in order to avoid
+ * exceeding MaxAllocSize - that could happen if the individual attributes are
+ * smaller than MaxAllocSize but the whole tuple is bigger.
+ */
+static HeapTuple
+restore_tuple(BufFile *file, Relation relation, MemoryContext cxt)
+{
+	uint32		t_len;
+	HeapTuple	tup;
+	MemoryContext oldcxt;
+	uint32		natt_ext;
+	List	   *attrs_ext = NIL;
+
+	oldcxt = MemoryContextSwitchTo(cxt);
+
+	/* First, read the external attributes if there are some. */
+	BufFileReadExact(file, &natt_ext, sizeof(natt_ext));
+	for (int i = 0; i < natt_ext; i++)
+	{
+		varlena		varhdr;
+		char	   *ext_val;
+		Size		ext_val_size;
+
+		/*
+		 * Read the header into properly aligned memory before accessing it.
+		 */
+		BufFileReadExact(file, &varhdr, VARHDRSZ);
+		ext_val_size = VARSIZE_ANY(&varhdr);
+		ext_val = palloc0(ext_val_size);
+		memcpy(ext_val, &varhdr, VARHDRSZ);
+		BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ);
+
+		attrs_ext = lappend(attrs_ext, ext_val);
+	}
+
+	/* Read the tuple. */
+	BufFileReadExact(file, &t_len, sizeof(t_len));
+	tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len);
+	tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE);
+	BufFileReadExact(file, tup->t_data, t_len);
+	tup->t_len = t_len;
+	ItemPointerSetInvalid(&tup->t_self);
+	tup->t_tableOid = RelationGetRelid(relation);
+
+	/*
+	 * If there are "external indirect" attributes, make the tuple reference
+	 * them.
+	 */
+	if (natt_ext > 0)
+	{
+		TupleDesc	desc;
+		Datum	   *attrs;
+		bool	   *isnull;
+		ListCell   *lc;
+
+		desc = RelationGetDescr(relation);
+		attrs = palloc0_array(Datum, desc->natts);
+		isnull = palloc0_array(bool, desc->natts);
+
+		heap_deform_tuple(tup, desc, attrs, isnull);
+
+		lc = list_head(attrs_ext);
+		for (int i = 0; i < desc->natts; i++)
+		{
+			CompactAttribute *attr = TupleDescCompactAttr(desc, i);
+			varlena    *varlena_pointer,
+					   *new_datum;
+			varatt_indirect redirect_pointer;
+
+			/* Find the external attributes, like in store_change(). */
+			if (attr->attisdropped)
+				continue;
+			if (attr->attlen != -1)
+				continue;
+			if (isnull[i])
+				continue;
+			varlena_pointer = (varlena *) DatumGetPointer(attrs[i]);
+			if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer))
+				continue;
+
+			/* Update the attribute. */
+			memset(&redirect_pointer, 0, sizeof(redirect_pointer));
+			redirect_pointer.pointer = lfirst(lc);
+
+			new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE);
+			SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT);
+			memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer,
+				   sizeof(redirect_pointer));
+
+			attrs[i] = PointerGetDatum(new_datum);
+
+			lc = lnext(attrs_ext, lc);
+		}
+		Assert(lc == NULL);
+
+		tup = heap_form_tuple(desc, attrs, isnull);
+	}
+
+	MemoryContextSwitchTo(oldcxt);
+
+	return tup;
+}
+
+/*
+ * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified
+ * 'tup_dst'. Use 'cxt' for all memory allocations.
+ */
+static HeapTuple
+adjust_toast_pointers(Relation relation, HeapTuple tup_dst,
+					  HeapTuple tup_src, MemoryContext cxt)
+{
+	TupleDesc	desc;
+	Datum	   *attrs_dst;
+	bool	   *isnull_dst;
+	Datum	   *attrs_src = NULL;
+	bool	   *isnull_src = NULL;
+	MemoryContext oldcxt;
+	HeapTuple	result;
+
+	oldcxt = MemoryContextSwitchTo(cxt);
+
+	desc = RelationGetDescr(relation);
+	attrs_dst = palloc0_array(Datum, desc->natts);
+	isnull_dst = palloc0_array(bool, desc->natts);
+
+	heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst);
+
+	for (int i = 0; i < desc->natts; i++)
+	{
+		CompactAttribute *attr = TupleDescCompactAttr(desc, i);
+		varlena    *varlena_dst,
+				   *varlena_src;
+
+		if (attr->attisdropped)
+			continue;
+		if (attr->attlen != -1)
+			continue;
+		if (isnull_dst[i])
+			continue;
+
+		varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]);
+		if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst))
+			continue;
+
+		/*
+		 * The first TOAST pointer? The caller can easily check if the tuple
+		 * has external attributes(s) in general, but is not supposed to check
+		 * specifically for TOAST.
+		 */
+		if (attrs_src == NULL)
+		{
+			attrs_src = palloc0_array(Datum, desc->natts);
+			isnull_src = palloc0_array(bool, desc->natts);
+
+			heap_deform_tuple(tup_src, desc, attrs_src, isnull_src);
+		}
+
+		varlena_src = (varlena *) DatumGetPointer(attrs_src[i]);
+
+		/*
+		 * Logical decoding only uses TOAST pointer for attributes that
+		 * haven't changed.
+		 */
+		Assert(!isnull_src[i]);
+		Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src));
+
+		/* Copy the pointer. */
+		memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src),
+			   sizeof(varatt_external));
+	}
+	result = heap_form_tuple(desc, attrs_dst, isnull_dst);
+
+	MemoryContextSwitchTo(oldcxt);
+
+	return result;
+}
+
 /*
  * Find the tuple to be updated or deleted.
  *
@@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate)
 static void
 cleanup_logical_decoding(LogicalDecodingContext *ctx)
 {
-	RepackDecodingState *dstate;
-
-	dstate = (RepackDecodingState *) ctx->output_writer_private;
-
-	FreeTupleDesc(dstate->tupdesc);
 	FreeDecodingContext(ctx);
-
 	ReplicationSlotDropAcquired();
-	pfree(dstate);
 }
 
 /*
diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
index d0c464a98d5..8e22aeb163b 100644
--- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c
+++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c
@@ -12,7 +12,7 @@
  */
 #include "postgres.h"
 
-#include "access/heaptoast.h"
+#include "access/detoast.h"
 #include "commands/cluster.h"
 #include "replication/snapbuild.h"
 #include "utils/memutils.h"
@@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx,
 							  ReorderBufferTXN *txn, XLogRecPtr commit_lsn);
 static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
 						  Relation rel, ReorderBufferChange *change);
-static void store_change(LogicalDecodingContext *ctx,
+static void store_change(LogicalDecodingContext *ctx, Relation relation,
 						 ConcurrentChangeKind kind, HeapTuple tuple);
 
 void
@@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
 
 	dstate = (RepackDecodingState *) ctx->output_writer_private;
 
-	/* Only interested in one particular relation. */
-	if (relation->rd_id != dstate->relid)
-		return;
+	/* Changes of other relation should not have been decoded. */
+	Assert(RelationGetRelid(relation) == dstate->relid);
 
 	/* Decode entry depending on its type */
 	switch (change->action)
@@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
 				if (newtuple == NULL)
 					elog(ERROR, "incomplete insert info.");
 
-				store_change(ctx, CHANGE_INSERT, newtuple);
+				store_change(ctx, relation, CHANGE_INSERT, newtuple);
 			}
 			break;
 		case REORDER_BUFFER_CHANGE_UPDATE:
@@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
 					elog(ERROR, "incomplete update info.");
 
 				if (oldtuple != NULL)
-					store_change(ctx, CHANGE_UPDATE_OLD, oldtuple);
+					store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple);
 
-				store_change(ctx, CHANGE_UPDATE_NEW, newtuple);
+				store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple);
 			}
 			break;
 		case REORDER_BUFFER_CHANGE_DELETE:
@@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
 				if (oldtuple == NULL)
 					elog(ERROR, "incomplete delete info.");
 
-				store_change(ctx, CHANGE_DELETE, oldtuple);
+				store_change(ctx, relation, CHANGE_DELETE, oldtuple);
 			}
 			break;
 		default:
@@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
 
 /* Store concurrent data change. */
 static void
-store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind,
-			 HeapTuple tuple)
+store_change(LogicalDecodingContext *ctx, Relation relation,
+			 ConcurrentChangeKind kind, HeapTuple tuple)
 {
 	RepackDecodingState *dstate;
+	BufFile    *file;
 	char		kind_byte = (char) kind;
-	bool		flattened = false;
+	List	   *attrs_ext = NIL;
+	uint32		natt_ext;
 
 	dstate = (RepackDecodingState *) ctx->output_writer_private;
+	file = dstate->file;
 
 	/* Store the change kind. */
-	BufFileWrite(dstate->file, &kind_byte, 1);
+	BufFileWrite(file, &kind_byte, 1);
 
 	/*
-	 * ReorderBufferCommit() stores the TOAST chunks in its private memory
-	 * context and frees them after having called apply_change().  Therefore
-	 * we need flat copy (including TOAST) that we eventually copy into the
-	 * memory context which is available to decode_concurrent_changes().
+	 * If the tuple contains "external indirect" attributes, we need to write
+	 * the contents to the file because we have no control over that memory.
 	 */
 	if (HeapTupleHasExternal(tuple))
 	{
-		/*
-		 * toast_flatten_tuple_to_datum() might be more convenient but we
-		 * don't want the decompression it does.
-		 */
-		tuple = toast_flatten_tuple(tuple, dstate->tupdesc);
-		flattened = true;
+		TupleDesc	desc;
+		Datum	   *attrs;
+		bool	   *isnull;
+
+		desc = RelationGetDescr(relation);
+		attrs = palloc0_array(Datum, desc->natts);
+		isnull = palloc0_array(bool, desc->natts);
+
+		heap_deform_tuple(tuple, desc, attrs, isnull);
+
+		/* First, gather and count the "external indirect" attributes. */
+		for (int i = 0; i < desc->natts; i++)
+		{
+			CompactAttribute *attr = TupleDescCompactAttr(desc, i);
+			varlena    *varlena_pointer;
+
+			if (attr->attisdropped)
+				continue;
+
+			/* not a varlena datatype */
+			if (attr->attlen != -1)
+				continue;
+
+			/* no data */
+			if (isnull[i])
+				continue;
+
+			/* ok, we know we have a toast datum */
+			varlena_pointer = (varlena *) DatumGetPointer(attrs[i]);
+
+			if (!VARATT_IS_EXTERNAL(varlena_pointer))
+				continue;
+
+			if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer))
+				attrs_ext = lappend(attrs_ext, varlena_pointer);
+			else
+			{
+				/*
+				 * Logical decoding should not produce "external expanded"
+				 * attributes (those actually should never appear on disk), so
+				 * only TOASTed attribute can be seen here.
+				 */
+				Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer));
+			}
+		}
+		natt_ext = list_length(attrs_ext);
 	}
-	/* Store the tuple size ... */
-	BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len));
-	/* ... and the tuple itself. */
-	BufFileWrite(dstate->file, tuple->t_data, tuple->t_len);
+	else
+		natt_ext = 0;
 
-	/* Free the flat copy if created above. */
-	if (flattened)
-		pfree(tuple);
+	/* Write the number of external attributes. */
+	BufFileWrite(file, &natt_ext, sizeof(natt_ext));
+	/* ... and the attributes themselves, if there are some. */
+	foreach_ptr(varlena, attr_val, attrs_ext)
+	{
+		varlena    *ext_val;
+		Size		ext_val_size;
+
+		ext_val = detoast_external_attr(attr_val);
+		ext_val_size = VARSIZE_ANY(ext_val);
+		BufFileWrite(file, ext_val, ext_val_size);
+		pfree(ext_val);
+	}
+	list_free(attrs_ext);
+
+	/* Finally write the tuple size ... */
+	BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len));
+	/* ... and the tuple itself. */
+	BufFileWrite(file, tuple->t_data, tuple->t_len);
 }
diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h
index 1b05d5d418b..a32813e8530 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -65,11 +65,10 @@ typedef enum
  */
 typedef struct RepackDecodingState
 {
+#ifdef	USE_ASSERT_CHECKING
 	/* The relation whose changes we're decoding. */
 	Oid			relid;
-
-	/* Tuple descriptor of the relation being processed. */
-	TupleDesc	tupdesc;
+#endif
 
 	/* The current output file. */
 	BufFile    *file;
diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out
index 4f866a74e32..b56dde134f8 100644
--- a/src/test/modules/injection_points/expected/repack_toast.out
+++ b/src/test/modules/injection_points/expected/repack_toast.out
@@ -13,6 +13,7 @@ step change:
 	UPDATE repack_test SET j=get_long_string() where i=2;
 	DELETE FROM repack_test WHERE i=3;
 	INSERT INTO repack_test(i, j) VALUES (4, get_long_string());
+	UPDATE repack_test SET i=3 where i=1;
 
 step check2: 
 	INSERT INTO relfilenodes(node)
diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec
index b48abf21450..f84917daca2 100644
--- a/src/test/modules/injection_points/specs/repack_toast.spec
+++ b/src/test/modules/injection_points/specs/repack_toast.spec
@@ -74,10 +74,17 @@ teardown
 
 session s2
 step change
+# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In
+# the first case, the new tuple we get from reorderbuffer.c contains "j" as a
+# TOAST pointer, wich we need to update so it points to the new heap. In the
+# latter case, we receive "j" as "external indirect" value - here we test that
+# the decoding worker writes the tuple to a file correctly and that the
+# backend executing REPACK manages to restore it.
 {
 	UPDATE repack_test SET j=get_long_string() where i=2;
 	DELETE FROM repack_test WHERE i=3;
 	INSERT INTO repack_test(i, j) VALUES (4, get_long_string());
+	UPDATE repack_test SET i=3 where i=1;
 }
 # Check the table from the perspective of s2.
 step check2
-- 
2.47.3


--=-=-=--





^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <alvherre@kurilemu.de>
  0 siblings, 0 replies; 382+ messages in thread

From: Álvaro Herrera @ 2026-03-31 14:48 UTC (permalink / raw)

---
 src/backend/commands/cluster.c | 163 +++++++++++----------------------
 1 file changed, 51 insertions(+), 112 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index fd0bfacaae6..c0220cb3380 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -2459,18 +2459,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	TupleTableSlot *spilled_tuple;
 	TupleTableSlot *old_update_tuple;
 	TupleTableSlot *ondisk_tuple;
-	MemoryContext apply_cxt;
 	bool		have_old_tuple = false;
-
-	/*
-	 * Use a separate memory context for the tuples and any memory needed to
-	 * process them.
-	 *
-	 * XXX would this be better with GenerationContextCreate?
-	 */
-	apply_cxt = AllocSetContextCreate(TopTransactionContext,
-									  "REPACK - apply",
-									  ALLOCSET_DEFAULT_SIZES);
+	MemoryContext	oldcxt;
 
 	spilled_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 											 &TTSOpsVirtual);
@@ -2479,6 +2469,8 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 	old_update_tuple = MakeSingleTupleTableSlot(RelationGetDescr(rel),
 												&TTSOpsVirtual);
 
+	oldcxt = MemoryContextSwitchTo(GetPerTupleMemoryContext(chgcxt->cc_estate));
+
 	while (true)
 	{
 		size_t		nread;
@@ -2570,14 +2562,15 @@ apply_concurrent_changes(BufFile *file, ChangeContext *chgcxt)
 		else
 			elog(ERROR, "unrecognized kind of change: %d", kind);
 
-		MemoryContextReset(apply_cxt);
+		ResetPerTupleExprContext(chgcxt->cc_estate);
 	}
 
 	/* Cleanup. */
 	ExecDropSingleTupleTableSlot(spilled_tuple);
 	ExecDropSingleTupleTableSlot(ondisk_tuple);
 	ExecDropSingleTupleTableSlot(old_update_tuple);
-	MemoryContextDelete(apply_cxt);
+
+	MemoryContextSwitchTo(oldcxt);
 }
 
 /*
@@ -2588,27 +2581,17 @@ static void
 apply_concurrent_insert(Relation rel, TupleTableSlot *slot,
 						ChangeContext *chgcxt)
 {
-	List	   *recheck;
-
 	/* Put the tuple in the table, but make sure it won't be decoded */
 	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
 					   HEAP_INSERT_NO_LOGICAL, NULL);
 
-	/*
-	 * Update indexes with this new tuple.  Because we're merely replaying an
-	 * action that already happened, we have no use for the recheck list of
-	 * indexes returned, so just free it.  XXX or maybe just leave it?
-	 */
-	recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-									chgcxt->cc_estate,
-									0,
-									slot,
-									NIL, NULL);
-	list_free(recheck);
-
+	/* Update indexes with this new tuple. */
+	ExecInsertIndexTuples(chgcxt->cc_rri,
+						  chgcxt->cc_estate,
+						  0,
+						  slot,
+						  NIL, NULL);
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, 1);
-
-	ResetPerTupleExprContext(chgcxt->cc_estate);
 }
 
 /*
@@ -2624,10 +2607,9 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 	TM_FailureData tmfd;
 	TU_UpdateIndexes update_indexes;
 	TM_Result	res;
-	List	   *recheck;
 
 	/*
-	 * Carry out the update, avoiding logical decoding info.
+	 * Carry out the update, skipping logical decoding for it.
 	 */
 	res = table_tuple_update(rel, &(ondisk_tuple->tts_tid), spilled_tuple,
 							 GetCurrentCommandId(true),
@@ -2646,13 +2628,11 @@ apply_concurrent_update(Relation rel, TupleTableSlot *spilled_tuple,
 
 		if (update_indexes == TU_Summarizing)
 			flags |= EIIT_ONLY_SUMMARIZING;
-		recheck = ExecInsertIndexTuples(chgcxt->cc_rri,
-										chgcxt->cc_estate,
-										flags,
-										spilled_tuple,
-										NIL, NULL);
-		list_free(recheck);
-		ResetPerTupleExprContext(chgcxt->cc_estate);
+		ExecInsertIndexTuples(chgcxt->cc_rri,
+							  chgcxt->cc_estate,
+							  flags,
+							  spilled_tuple,
+							  NIL, NULL);
 	}
 
 	pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_UPDATED, 1);
@@ -2665,10 +2645,7 @@ apply_concurrent_delete(Relation rel, TupleTableSlot *slot)
 	TM_FailureData tmfd;
 
 	/*
-	 * Delete tuple from the new heap.
-	 *
-	 * Do it like in simple_heap_delete(), except for 'wal_logical' (and
-	 * except for 'wait').
+	 * Delete tuple from the new heap, skipping logical decoding for it.
 	 */
 	res = table_tuple_delete(rel, &(slot->tts_tid),
 							 GetCurrentCommandId(true),
@@ -3009,12 +2986,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	char		relpersistence;
 	bool		is_system_catalog;
 	Oid			ident_idx_new;
-	XLogRecPtr	wal_insert_ptr,
-				end_of_wal;
-	char		dummy_rec_data = '\0';
-	Relation   *ind_refs,
-			   *ind_refs_p;
-	int			nind;
+	XLogRecPtr	end_of_wal;
+	List	   *indexrels;
 	ChangeContext chgcxt;
 
 	/* Like in cluster_rel(). */
@@ -3041,24 +3014,23 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 */
 	ind_oids_new = build_new_indexes(NewHeap, OldHeap, ind_oids_old);
 
-	/* Find "identity index" on the new relation. */
+	/*
+	 * The identity index in the new relation appears in the same relative
+	 * position as the corresponding index in the old relation.  Find it.
+	 */
 	ident_idx_new = InvalidOid;
-	forboth(lc, ind_oids_old, lc2, ind_oids_new)
+	foreach_oid(ind_old, ind_oids_old)
 	{
-		Oid			ind_old = lfirst_oid(lc);
-		Oid			ind_new = lfirst_oid(lc2);
-
 		if (identIdx == ind_old)
 		{
-			ident_idx_new = ind_new;
+			ident_idx_new = list_nth_oid(ind_oids_new,
+										 foreach_current_index(ind_old));
 			break;
 		}
 	}
-
-	/* Should not happen, given our lock on the old relation. */
 	if (!OidIsValid(ident_idx_new))
-		ereport(ERROR,
-				errmsg("identity index missing on the new relation"));
+		elog(ERROR, "could not find index matching \"%s\" at the new relation",
+			 get_rel_name(identIdx));
 
 	/* Gather information to apply concurrent changes. */
 	initialize_change_context(&chgcxt, NewHeap, ident_idx_new);
@@ -3074,8 +3046,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * incomplete page; see GetInsertRecPtr), to minimize the amount of data
 	 * we need to flush while holding exclusive lock on the source table.
 	 */
-	wal_insert_ptr = GetInsertRecPtr();
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3094,10 +3065,9 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	/*
 	 * Lock all indexes now, not only the clustering one: all indexes need to
 	 * have their files swapped. While doing that, store their relation
-	 * references in an array, to handle predicate locks below.
+	 * references in a zero-terminated array, to handle predicate locks below.
 	 */
-	ind_refs_p = ind_refs = palloc_array(Relation, list_length(ind_oids_old));
-	nind = 0;
+	indexrels = NIL;
 	foreach_oid(ind_oid, ind_oids_old)
 	{
 		Relation	index;
@@ -3105,16 +3075,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 		index = index_open(ind_oid, AccessExclusiveLock);
 
 		/*
-		 * TODO 1) Do we need to check if ALTER INDEX was executed since the
-		 * new index was created in build_new_indexes()? 2) Specifically for
-		 * the clustering index, should check_index_is_clusterable() be called
-		 * here? (Not sure about the latter: ShareUpdateExclusiveLock on the
-		 * table probably blocks all commands that affect the result of
-		 * check_index_is_clusterable().)
+		 * Some things about the index may have changed before we locked the
+		 * index, such as ALTER INDEX RENAME.  We don't need to do anything
+		 * here to absorb those changes in the new index.
 		 */
-		*ind_refs_p = index;
-		ind_refs_p++;
-		nind++;
+		indexrels = lappend(indexrels, index);
 	}
 
 	/*
@@ -3128,40 +3093,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	 * Tuples and pages of the old heap will be gone, but the heap will stay.
 	 */
 	TransferPredicateLocksToHeapRelation(OldHeap);
-	/* The same for indexes. */
-	for (int i = 0; i < nind; i++)
+	foreach_ptr(RelationData, index, indexrels)
 	{
-		Relation	index = ind_refs[i];
-
 		TransferPredicateLocksToHeapRelation(index);
-
-		/*
-		 * References to indexes on the old relation are not needed anymore,
-		 * however locks stay till the end of the transaction.
-		 */
 		index_close(index, NoLock);
 	}
-	pfree(ind_refs);
+	list_free(indexrels);
 
 	/*
-	 * Flush anything we see in WAL, to make sure that all changes committed
-	 * while we were waiting for the exclusive lock are available for
-	 * decoding. This should not be necessary if all backends had
-	 * synchronous_commit set, but we can't rely on this setting.
-	 *
-	 * Unfortunately, GetInsertRecPtr() may lag behind the actual insert
-	 * position, and GetLastImportantRecPtr() points at the start of the last
-	 * record rather than at the end. Thus the simplest way to determine the
-	 * insert position is to insert a dummy record and use its LSN.
-	 *
-	 * XXX Consider using GetLastImportantRecPtr() and adding the size of the
-	 * last record (plus the total size of all the page headers the record
-	 * spans)?
+	 * Flush WAL again, to make sure that all changes committed while we were
+	 * waiting for the exclusive lock are available for decoding.
 	 */
-	XLogBeginInsert();
-	XLogRegisterData(&dummy_rec_data, 1);
-	wal_insert_ptr = XLogInsert(RM_XLOG_ID, XLOG_NOOP);
-	XLogFlush(wal_insert_ptr);
+	XLogFlush(GetXLogInsertRecPtr());
 	end_of_wal = GetFlushRecPtr(NULL);
 
 	/*
@@ -3186,10 +3129,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 	{
 		Oid			ind_old = lfirst_oid(lc);
 		Oid			ind_new = lfirst_oid(lc2);
-		Oid			mapped_tables[4];
-
-		/* Zero out possible results from swapped_relation_files */
-		memset(mapped_tables, 0, sizeof(mapped_tables));
+		Oid			mapped_tables[4] = {0};
 
 		swap_relation_files(ind_old, ind_new,
 							(old_table_oid == RelationRelationId),
@@ -3200,13 +3140,12 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							mapped_tables);
 
 #ifdef USE_ASSERT_CHECKING
-
 		/*
 		 * Concurrent processing is not supported for system relations, so
 		 * there should be no mapped tables.
 		 */
 		for (int i = 0; i < 4; i++)
-			Assert(mapped_tables[i] == 0);
+			Assert(!OidIsValid(mapped_tables[i]));
 #endif
 	}
 
@@ -3256,22 +3195,22 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes)
 	pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 								 PROGRESS_REPACK_PHASE_REBUILD_INDEX);
 
-	foreach_oid(ind_oid, OldIndexes)
+	foreach_oid(oldindex, OldIndexes)
 	{
-		Oid			ind_oid_new;
+		Oid			newindex;
 		char	   *newName;
 		Relation	ind;
 
-		ind = index_open(ind_oid, ShareUpdateExclusiveLock);
+		ind = index_open(oldindex, ShareUpdateExclusiveLock);
 
-		newName = ChooseRelationName(get_rel_name(ind_oid),
+		newName = ChooseRelationName(get_rel_name(oldindex),
 									 NULL,
 									 "repacknew",
 									 get_rel_namespace(ind->rd_index->indrelid),
 									 false);
-		ind_oid_new = index_create_copy(NewHeap, false, ind_oid,
-										ind->rd_rel->reltablespace, newName);
-		result = lappend_oid(result, ind_oid_new);
+		newindex = index_create_copy(NewHeap, false, oldindex,
+									 ind->rd_rel->reltablespace, newName);
+		result = lappend_oid(result, newindex);
 
 		index_close(ind, NoLock);
 	}
-- 
2.47.3


--2fxmamo6mu2qbxgv
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="v47-0005-Use-BulkInsertState-when-copying-data-to-the-new.patch"



^ permalink  raw  reply  [nested|flat] 382+ messages in thread