agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v7 2/7] Row pattern recognition patch (parse/analysis).
9657+ messages / 2 participants
[nested] [flat]

* [PATCH v7 2/7] Row pattern recognition patch (parse/analysis).
@ 2023-09-22 04:53  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

From: Tatsuo Ishii @ 2023-09-22 04:53 UTC (permalink / raw)

---
 src/backend/parser/parse_agg.c    |   7 +
 src/backend/parser/parse_clause.c | 293 +++++++++++++++++++++++++++++-
 src/backend/parser/parse_expr.c   |   4 +
 src/backend/parser/parse_func.c   |   3 +
 4 files changed, 306 insertions(+), 1 deletion(-)

diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c
index 85cd47b7ae..aa7a1cee80 100644
--- a/src/backend/parser/parse_agg.c
+++ b/src/backend/parser/parse_agg.c
@@ -564,6 +564,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr)
 			errkind = true;
 			break;
 
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
+
 			/*
 			 * There is intentionally no default: case here, so that the
 			 * compiler will warn if we add a new ParseExprKind without
@@ -953,6 +957,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc,
 		case EXPR_KIND_CYCLE_MARK:
 			errkind = true;
 			break;
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
 
 			/*
 			 * There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c
index 334b9b42bd..293d4b1680 100644
--- a/src/backend/parser/parse_clause.c
+++ b/src/backend/parser/parse_clause.c
@@ -100,7 +100,10 @@ static WindowClause *findWindowClause(List *wclist, const char *name);
 static Node *transformFrameOffset(ParseState *pstate, int frameOptions,
 								  Oid rangeopfamily, Oid rangeopcintype, Oid *inRangeFunc,
 								  Node *clause);
-
+static void transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef, List **targetlist);
+static List *transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef, List **targetlist);
+static void transformPatternClause(ParseState *pstate, WindowClause *wc, WindowDef *windef);
+static List *transformMeasureClause(ParseState *pstate, WindowClause *wc, WindowDef *windef);
 
 /*
  * transformFromClause -
@@ -2950,6 +2953,10 @@ transformWindowDefinitions(ParseState *pstate,
 											 rangeopfamily, rangeopcintype,
 											 &wc->endInRangeFunc,
 											 windef->endOffset);
+
+		/* Process Row Pattern Recognition related clauses */
+		transformRPR(pstate, wc, windef, targetlist);
+
 		wc->runCondition = NIL;
 		wc->winref = winref;
 
@@ -3815,3 +3822,287 @@ transformFrameOffset(ParseState *pstate, int frameOptions,
 
 	return node;
 }
+
+/*
+ * transformRPR
+ *		Process Row Pattern Recognition related clauses
+ */
+static void
+transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef, List **targetlist)
+{
+	/*
+	 * Window definition exists?
+	 */
+	if (windef == NULL)
+		return;
+
+	/*
+	 * Row Pattern Common Syntax clause exists?
+	 */
+	if (windef->rpCommonSyntax == NULL)
+		return;
+
+	/* Check Frame option. Frame must start at current row */
+	if ((wc->frameOptions & FRAMEOPTION_START_CURRENT_ROW) == 0)
+		ereport(ERROR,
+				(errcode(ERRCODE_SYNTAX_ERROR),
+				 errmsg("FRAME must start at current row when row patttern recognition is used")));
+
+	/* Transform AFTER MACH SKIP TO clause */
+	wc->rpSkipTo = windef->rpCommonSyntax->rpSkipTo;
+
+	/* Transform SEEK or INITIAL clause */
+	wc->initial = windef->rpCommonSyntax->initial;
+
+	/* Transform DEFINE clause into list of TargetEntry's */
+	wc->defineClause = transformDefineClause(pstate, wc, windef, targetlist);
+
+	/* Check PATTERN clause and copy to patternClause */
+	transformPatternClause(pstate, wc, windef);
+
+	/* Transform MEASURE clause */
+	transformMeasureClause(pstate, wc, windef);
+}
+
+/*
+ * transformDefineClause Process DEFINE clause and transform ResTarget into
+ *		list of TargetEntry.
+ *
+ * XXX we only support column reference in row pattern definition search
+ * condition, e.g. "price". <row pattern definition variable name>.<column
+ * reference> is not supported, e.g. "A.price".
+ */
+static List *
+transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef, List **targetlist)
+{
+	/* DEFINE variable name initials */
+	static	char	*defineVariableInitials = "abcdefghijklmnopqrstuvwxyz";
+
+	ListCell		*lc, *l;
+	ResTarget		*restarget, *r;
+	List			*restargets;
+	char			*name;
+	int				initialLen;
+	int				i;
+
+	/*
+	 * If Row Definition Common Syntax exists, DEFINE clause must exist.
+	 * (the raw parser should have already checked it.)
+	 */
+	Assert(windef->rpCommonSyntax->rpDefs != NULL);
+
+	/*
+	 * Check and add "A AS A IS TRUE" if pattern variable is missing in DEFINE
+	 * per the SQL standard.
+	 */
+	restargets = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpPatterns)
+	{
+		A_Expr	*a;
+		bool	found = false;
+
+		if (!IsA(lfirst(lc), A_Expr))
+			ereport(ERROR,
+					errmsg("node type is not A_Expr"));
+
+		a = (A_Expr *)lfirst(lc);
+		name = strVal(a->lexpr);
+
+		foreach(l, windef->rpCommonSyntax->rpDefs)
+		{
+			restarget = (ResTarget *)lfirst(l);
+
+			if (!strcmp(restarget->name, name))
+			{
+				found = true;
+				break;
+			}
+		}
+
+		if (!found)
+		{
+			/*
+			 * "name" is missing. So create "name AS name IS TRUE" ResTarget
+			 * node and add it to the temporary list.
+			 */
+			A_Const	   *n;
+
+			restarget = makeNode(ResTarget);
+			n = makeNode(A_Const);
+			n->val.boolval.type = T_Boolean;
+			n->val.boolval.boolval = true;
+			n->location = -1;
+			restarget->name = pstrdup(name);
+			restarget->indirection = NIL;
+			restarget->val = (Node *)n;
+			restarget->location = -1;
+			restargets = lappend((List *)restargets, restarget);
+		}
+	}
+
+	if (list_length(restargets) >= 1)
+	{
+		/* add missing DEFINEs */
+		windef->rpCommonSyntax->rpDefs = list_concat(windef->rpCommonSyntax->rpDefs,
+													 restargets);
+		list_free(restargets);
+	}
+
+	/*
+	 * Check for duplicate row pattern definition variables.  The standard
+	 * requires that no two row pattern definition variable names shall be
+	 * equivalent.
+	 */
+	restargets = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpDefs)
+	{
+		restarget = (ResTarget *)lfirst(lc);
+		name = restarget->name;
+
+		/*
+		 * Add DEFINE expression (Restarget->val) to the targetlist as a
+		 * TargetEntry if it does not exist yet. Planner will add the column
+		 * ref var node to the outer plan's target list later on. This makes
+		 * DEFINE expression could access the outer tuple while evaluating
+		 * PATTERN.
+		 *
+		 * XXX: adding whole expressions of DEFINE to the plan.targetlist is
+		 * not so good, because it's not necessary to evalute the expression
+		 * in the target list while running the plan. We should extract the
+		 * var nodes only then add them to the plan.targetlist.
+		 */
+		findTargetlistEntrySQL99(pstate, (Node *)restarget->val, targetlist, EXPR_KIND_RPR_DEFINE);
+
+		/*
+		 * Make sure that the row pattern definition search condition is a
+		 * boolean expression.
+		 */
+		transformWhereClause(pstate, restarget->val,
+							 EXPR_KIND_RPR_DEFINE, "DEFINE");
+
+		foreach(l, restargets)
+		{
+			char		*n;
+
+			r = (ResTarget *) lfirst(l);
+			n = r->name;
+
+			if (!strcmp(n, name))
+				ereport(ERROR,
+						(errcode(ERRCODE_SYNTAX_ERROR),
+						 errmsg("row pattern definition variable name \"%s\" appears more than once in DEFINE clause",
+								name),
+						 parser_errposition(pstate, exprLocation((Node *)r))));
+		}
+		restargets = lappend(restargets, restarget);
+	}
+	list_free(restargets);
+
+	/*
+	 * Create list of row pattern DEFINE variable name's initial.
+	 * We assign [a-z] to them (up to 26 variable names are allowed).
+	 */
+	restargets = NIL;
+	i = 0;
+	initialLen = strlen(defineVariableInitials);
+
+	foreach(lc, windef->rpCommonSyntax->rpDefs)
+	{
+		char	initial[2];
+
+		restarget = (ResTarget *)lfirst(lc);
+		name = restarget->name;
+
+		if (i >= initialLen)
+		{
+			ereport(ERROR,
+					(errcode(ERRCODE_SYNTAX_ERROR),
+					 errmsg("number of row pattern definition variable names exceeds %d", initialLen),
+					 parser_errposition(pstate, exprLocation((Node *)restarget))));
+		}
+		initial[0] = defineVariableInitials[i++];
+		initial[1] = '\0';
+		wc->defineInitial = lappend(wc->defineInitial, makeString(pstrdup(initial)));
+	}
+
+	return transformTargetList(pstate, windef->rpCommonSyntax->rpDefs,
+							   EXPR_KIND_RPR_DEFINE);
+}
+
+/*
+ * transformPatternClause
+ *		Process PATTERN clause and return PATTERN clause in the raw parse tree
+ */
+static void
+transformPatternClause(ParseState *pstate, WindowClause *wc, WindowDef *windef)
+{
+	ListCell	*lc, *l;
+
+	/*
+	 * Row Pattern Common Syntax clause exists?
+	 */
+	if (windef->rpCommonSyntax == NULL)
+		return;
+
+	/*
+	 * Primary row pattern variable names in PATTERN clause must appear in
+	 * DEFINE clause as row pattern definition variable names.
+	 */
+	wc->patternVariable = NIL;
+	wc->patternRegexp = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpPatterns)
+	{
+		A_Expr	*a;
+		char	*name;
+		char	*regexp;
+		bool	found = false;
+
+		if (!IsA(lfirst(lc), A_Expr))
+			ereport(ERROR,
+					errmsg("node type is not A_Expr"));
+
+		a = (A_Expr *)lfirst(lc);
+		name = strVal(a->lexpr);
+
+		foreach(l, windef->rpCommonSyntax->rpDefs)
+		{
+			ResTarget	*restarget = (ResTarget *)lfirst(l);
+
+			if (!strcmp(restarget->name, name))
+			{
+				found = true;
+				break;
+			}
+		}
+
+		if (!found)
+		{
+			ereport(ERROR,
+					(errcode(ERRCODE_SYNTAX_ERROR),
+					 errmsg("primary row pattern variable name \"%s\" does not appear in DEFINE clause",
+							name),
+					 parser_errposition(pstate, exprLocation((Node *)a))));
+		}
+		wc->patternVariable = lappend(wc->patternVariable, makeString(pstrdup(name)));
+		regexp = strVal(lfirst(list_head(a->name)));
+		wc->patternRegexp = lappend(wc->patternRegexp, makeString(pstrdup(regexp)));
+	}
+}
+
+/*
+ * transformMeasureClause
+ *		Process MEASURE clause
+ *	XXX MEASURE clause is not supported yet
+ */
+static List *
+transformMeasureClause(ParseState *pstate, WindowClause *wc, WindowDef *windef)
+{
+	if (windef->rowPatternMeasures == NIL)
+		return NIL;
+
+	ereport(ERROR,
+			(errcode(ERRCODE_SYNTAX_ERROR),
+			 errmsg("%s","MEASURE clause is not supported yet"),
+			 parser_errposition(pstate, exprLocation((Node *)windef->rowPatternMeasures))));
+	return NIL;
+}
diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c
index 64c582c344..18b58ac263 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -557,6 +557,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref)
 		case EXPR_KIND_COPY_WHERE:
 		case EXPR_KIND_GENERATED_COLUMN:
 		case EXPR_KIND_CYCLE_MARK:
+		case EXPR_KIND_RPR_DEFINE:
 			/* okay */
 			break;
 
@@ -1770,6 +1771,7 @@ transformSubLink(ParseState *pstate, SubLink *sublink)
 		case EXPR_KIND_VALUES:
 		case EXPR_KIND_VALUES_SINGLE:
 		case EXPR_KIND_CYCLE_MARK:
+		case EXPR_KIND_RPR_DEFINE:
 			/* okay */
 			break;
 		case EXPR_KIND_CHECK_CONSTRAINT:
@@ -3149,6 +3151,8 @@ ParseExprKindName(ParseExprKind exprKind)
 			return "GENERATED AS";
 		case EXPR_KIND_CYCLE_MARK:
 			return "CYCLE";
+		case EXPR_KIND_RPR_DEFINE:
+			return "DEFINE";
 
 			/*
 			 * There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_func.c b/src/backend/parser/parse_func.c
index b3f0b6a137..2ff3699538 100644
--- a/src/backend/parser/parse_func.c
+++ b/src/backend/parser/parse_func.c
@@ -2656,6 +2656,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location)
 		case EXPR_KIND_CYCLE_MARK:
 			errkind = true;
 			break;
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
 
 			/*
 			 * There is intentionally no default: case here, so that the
-- 
2.25.1


----Next_Part(Fri_Sep_22_14_16_40_2023_530)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v7-0003-Row-pattern-recognition-patch-planner.patch"



^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread

* [PATCH 5/5] Use BulkInsertState when copying data to the new heap.
@ 2026-03-05 18:58  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 9657+ messages in thread

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

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

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

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


--=-=-=--





^ permalink  raw  reply  [nested|flat] 9657+ messages in thread