agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v21 2/8] Row pattern recognition patch (parse/analysis).
220+ messages / 2 participants
[nested] [flat]

* [PATCH v21 2/8] Row pattern recognition patch (parse/analysis).
@ 2024-08-26 04:32  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Tatsuo Ishii @ 2024-08-26 04:32 UTC (permalink / raw)

---
 src/backend/parser/parse_agg.c    |   7 +
 src/backend/parser/parse_clause.c | 296 +++++++++++++++++++++++++++++-
 src/backend/parser/parse_expr.c   |   6 +
 src/backend/parser/parse_func.c   |   3 +
 4 files changed, 311 insertions(+), 1 deletion(-)

diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c
index bee7d8346a..9bc22a836a 100644
--- a/src/backend/parser/parse_agg.c
+++ b/src/backend/parser/parse_agg.c
@@ -577,6 +577,10 @@ 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
@@ -967,6 +971,9 @@ 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 8118036495..9762dce81f 100644
--- a/src/backend/parser/parse_clause.c
+++ b/src/backend/parser/parse_clause.c
@@ -98,7 +98,14 @@ 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 -
@@ -2956,6 +2963,10 @@ transformWindowDefinitions(ParseState *pstate,
 											 rangeopfamily, rangeopcintype,
 											 &wc->endInRangeFunc,
 											 windef->endOffset);
+
+		/* Process Row Pattern Recognition related clauses */
+		transformRPR(pstate, wc, windef, targetlist);
+
 		wc->winref = winref;
 
 		result = lappend(result, wc);
@@ -3820,3 +3831,286 @@ 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 AFTER MACH SKIP TO variable */
+	wc->rpSkipVariable = windef->rpCommonSyntax->rpSkipVariable;
+
+	/* 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;
+	List	   *defineClause;
+	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)));
+	}
+
+	defineClause = transformTargetList(pstate, windef->rpCommonSyntax->rpDefs,
+									   EXPR_KIND_RPR_DEFINE);
+
+	/* mark column origins */
+	markTargetListOrigins(pstate, defineClause);
+
+	/* mark all nodes in the DEFINE clause tree with collation information */
+	assign_expr_collations(pstate, (Node *) defineClause);
+
+	return defineClause;
+}
+
+/*
+ * transformPatternClause
+ *		Process PATTERN clause and return PATTERN clause in the raw parse tree
+ */
+static void
+transformPatternClause(ParseState *pstate, WindowClause *wc,
+					   WindowDef *windef)
+{
+	ListCell   *lc;
+
+	/*
+	 * Row Pattern Common Syntax clause exists?
+	 */
+	if (windef->rpCommonSyntax == NULL)
+		return;
+
+	wc->patternVariable = NIL;
+	wc->patternRegexp = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpPatterns)
+	{
+		A_Expr	   *a;
+		char	   *name;
+		char	   *regexp;
+
+		if (!IsA(lfirst(lc), A_Expr))
+			ereport(ERROR,
+					errmsg("node type is not A_Expr"));
+
+		a = (A_Expr *) lfirst(lc);
+		name = strVal(a->lexpr);
+
+		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 56e413da9f..c187b3278d 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -577,6 +577,7 @@ 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;
 
@@ -1860,6 +1861,9 @@ transformSubLink(ParseState *pstate, SubLink *sublink)
 		case EXPR_KIND_GENERATED_COLUMN:
 			err = _("cannot use subquery in column generation expression");
 			break;
+		case EXPR_KIND_RPR_DEFINE:
+			err = _("cannot use subquery in DEFINE expression");
+			break;
 
 			/*
 			 * There is intentionally no default: case here, so that the
@@ -3199,6 +3203,8 @@ 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 9b23344a3b..4c482abb30 100644
--- a/src/backend/parser/parse_func.c
+++ b/src/backend/parser/parse_func.c
@@ -2658,6 +2658,9 @@ 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(Mon_Aug_26_13_39_47_2024_878)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v21-0003-Row-pattern-recognition-patch-rewriter.patch"



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread

* [PATCH 1/8] Use tuple slot to pass tuples for rewriting.
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 220+ messages in thread

From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw)

This patch tries to adopt the preferable way of handling tuples, i.e. pass the
containing tuple slot rather than the actual tuple. The motivation is that
heap_insert_for_repack() will need a slot in the near future, in order to call
ExecInsertIndexTuples(). Also, in order to set values of dropped attributes to
to NULL, it seems more compact to pass a tuple slot as a workspace than two
arrays (one for values and one for nulls).
---
 src/backend/access/heap/heapam_handler.c | 199 +++++++++++++----------
 1 file changed, 110 insertions(+), 89 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index 2268cc277bc..127d4415084 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -48,14 +48,13 @@
 #include "utils/rel.h"
 #include "utils/tuplesort.h"
 
-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 void reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+									 RewriteState rwstate);
+static void heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+								   TupleTableSlot *reform,
+								   BulkInsertStateData *bistate);
+static bool tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc);
+static void clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform);
 
 static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 								   HeapTuple tuple,
@@ -609,11 +608,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	bool		is_system_catalog;
 	Tuplesortstate *tuplesort;
 	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
 	TupleTableSlot *slot;
-	int			natts;
-	Datum	   *values;
-	bool	   *isnull;
+	TupleTableSlot *reform_slot;
 	BufferHeapTupleTableSlot *hslot;
 	BlockNumber prev_cblock = InvalidBlockNumber;
 	bool		concurrent = snapshot != NULL;
@@ -627,11 +623,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 	 */
 	Assert(RelationGetTargetBlock(NewHeap) == InvalidBlockNumber);
 
-	/* Preallocate values/isnull arrays */
-	natts = newTupDesc->natts;
-	values = palloc_array(Datum, natts);
-	isnull = palloc_array(bool, natts);
-
 	/*
 	 * In non-concurrent mode, initialize the rewrite operation.  This is not
 	 * needed in concurrent mode.
@@ -705,6 +696,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 
 	slot = table_slot_create(OldHeap, NULL);
 	hslot = (BufferHeapTupleTableSlot *) slot;
+	reform_slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										   &TTSOpsVirtual);
 
 	/*
 	 * Scan through the OldHeap, either in OldIndex order or sequentially;
@@ -881,11 +874,9 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			int64		ct_val[2];
 
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple, OldHeap, NewHeap,
-										 values, isnull, rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/*
 			 * In indexscan mode and also VACUUM FULL, report increase in
@@ -901,8 +892,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		index_endscan(indexScan);
 	if (tableScan != NULL)
 		table_endscan(tableScan);
-	if (slot)
-		ExecDropSingleTupleTableSlot(slot);
+	ExecDropSingleTupleTableSlot(slot);
 
 	/*
 	 * In scan-and-sort mode, complete the sort, then read out all live tuples
@@ -922,6 +912,8 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 		pgstat_progress_update_param(PROGRESS_REPACK_PHASE,
 									 PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP);
 
+		slot = MakeSingleTupleTableSlot(RelationGetDescr(OldHeap),
+										&TTSOpsHeapTuple);
 		for (;;)
 		{
 			HeapTuple	tuple;
@@ -932,33 +924,36 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap,
 			if (tuple == NULL)
 				break;
 
+			/*
+			 * XXX Ideally we should use tuplesort_gettupleslot() above, but
+			 * it retrieves minimal tuples and tuplesort_puttupleslot() cannot
+			 * get the tuple descriptor from tuplesort created by
+			 * tuplesort_begin_cluster().
+			 */
+			ExecStoreHeapTuple(tuple, slot, false);
+
 			n_tuples += 1;
 			if (!concurrent)
-				reform_and_rewrite_tuple(tuple,
-										 OldHeap, NewHeap,
-										 values, isnull,
-										 rwstate);
+				reform_and_rewrite_tuple(slot, reform_slot, rwstate);
 			else
-				heap_insert_for_repack(tuple, OldHeap, NewHeap,
-									   values, isnull, bistate);
+				heap_insert_for_repack(NewHeap, slot, reform_slot, bistate);
 
 			/* Report n_tuples */
 			pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED,
 										 n_tuples);
 		}
 
+		ExecDropSingleTupleTableSlot(slot);
 		tuplesort_end(tuplesort);
 	}
 
+	ExecDropSingleTupleTableSlot(reform_slot);
+
 	/* Write out any remaining tuples, and fsync if needed */
 	if (rwstate)
 		end_heap_rewrite(rwstate);
 	if (bistate)
 		FreeBulkInsertState(bistate);
-
-	/* Clean up */
-	pfree(values);
-	pfree(isnull);
 }
 
 /*
@@ -2346,21 +2341,45 @@ heapam_scan_sample_next_tuple(TableScanDesc scan, SampleScanState *scanstate,
  * currently only known to happen as an after-effect of ALTER TABLE
  * SET WITHOUT OIDS.
  *
- * So, we must reconstruct the tuple from component Datums.
+ * So, we must reconstruct the tuple from component Datums. 'reform' slot
+ * is a workspace for this reconstruction.
  */
 static void
-reform_and_rewrite_tuple(HeapTuple tuple,
-						 Relation OldHeap, Relation NewHeap,
-						 Datum *values, bool *isnull, RewriteState rwstate)
+reform_and_rewrite_tuple(TupleTableSlot *src, TupleTableSlot *reform,
+						 RewriteState rwstate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple,
+				newtuple;
+	bool		shouldFree,
+				shouldFreeNew;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	/*
+	 * The old tuple will not be modified, so do not request materialization.
+	 * (A copy can be created for specific slot type though, e.g.
+	 * TTSOpsMinimalTuple.)
+	 */
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+
+		/* No need to materialize, copy will be created anyway. */
+		Assert(TTS_IS_VIRTUAL(reform));
+		newtuple = ExecFetchSlotHeapTuple(reform, false, &shouldFreeNew);
+	}
+	else
+	{
+		newtuple = heap_copytuple(tuple);
+		shouldFreeNew = true;
+	}
 
 	/* The heap rewrite module does the rest */
 	rewrite_heap_tuple(rwstate, tuple, newtuple);
 
-	heap_freetuple(newtuple);
+	if (shouldFree)
+		heap_freetuple(tuple);
+	if (shouldFreeNew)
+		heap_freetuple(newtuple);
 }
 
 /*
@@ -2372,6 +2391,9 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * information). Thus we must use heap_insert() both during the
  * catch-up and here.
  *
+ * 'reform' is a slot to use for tuple "reforming", typically to get set
+ * values of dropped columns to NULL.
+ *
  * 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.
@@ -2380,76 +2402,75 @@ reform_and_rewrite_tuple(HeapTuple tuple,
  * case.
  */
 static void
-heap_insert_for_repack(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-					   Datum *values, bool *isnull, BulkInsertState bistate)
+heap_insert_for_repack(Relation rel, TupleTableSlot *src,
+					   TupleTableSlot *reform, BulkInsertStateData *bistate)
 {
-	HeapTuple	newtuple;
+	HeapTuple	tuple;
+	bool		shouldFree;
+	TupleTableSlot *slot;
 
-	newtuple = reform_tuple(tuple, OldHeap, NewHeap, values, isnull);
+	tuple = ExecFetchSlotHeapTuple(src, false, &shouldFree);
+	if (tuple_needs_reform(tuple, src->tts_tupleDescriptor))
+	{
+		clear_dropped_attributes(tuple, reform);
+		slot = reform;
+	}
+	else
+		slot = src;
 
-	heap_insert(NewHeap, newtuple, GetCurrentCommandId(true),
-				HEAP_INSERT_NO_LOGICAL, bistate);
+	/*
+	 * clear_dropped_attributes() should have deformed the tuple, so nothing
+	 * should depend on it now.
+	 */
+	if (shouldFree)
+		heap_freetuple(tuple);
 
-	heap_freetuple(newtuple);
+	table_tuple_insert(rel, slot, GetCurrentCommandId(true),
+					   TABLE_INSERT_NO_LOGICAL, bistate);
 }
 
-/*
- * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
- *
- * Deform the given tuple, set values of dropped columns to NULL, and fill in
- * any values from attmissingval; then form a new tuple and return it.  If no
- * attributes need to be changed, a copy of the original tuple is returned.
- * Caller is responsible for freeing the returned tuple.
- *
- * XXX this coding assumes that both relations have the same tupledesc.
- */
-static HeapTuple
-reform_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap,
-			 Datum *values, bool *isnull)
+static bool
+tuple_needs_reform(HeapTuple tuple, TupleDesc tupDesc)
 {
-	TupleDesc	oldTupDesc = RelationGetDescr(OldHeap);
-	TupleDesc	newTupDesc = RelationGetDescr(NewHeap);
-	bool		needs_reform = false;
-
 	/*
 	 * A short tuple might require values from attmissing val, so activate the
 	 * coding unconditionally in that case.  The value might legitimally be
 	 * NULL otherwise, so this is slightly wasteful, but it probably beats
 	 * having to test each attribute for presence of attmissingval each time.
 	 */
-	if (HeapTupleHeaderGetNatts(tuple->t_data) < newTupDesc->natts)
-		needs_reform = true;
+	if (HeapTupleHeaderGetNatts(tuple->t_data) < tupDesc->natts)
+		return true;
 
-	/*
-	 * If the column has been dropped but a value is still present, we can
-	 * optimize storage now by getting rid of it.
-	 */
-	if (!needs_reform)
+	/* Does it have dropped attributes? */
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		for (int i = 0; i < newTupDesc->natts; i++)
-		{
-			if (TupleDescCompactAttr(newTupDesc, i)->attisdropped &&
-				!heap_attisnull(tuple, i + 1, newTupDesc))
-			{
-				needs_reform = true;
-				break;
-			}
-		}
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped &&
+			!heap_attisnull(tuple, i + 1, tupDesc))
+			return true;
 	}
 
-	/* Skip work if no changes are needed */
-	if (!needs_reform)
-		return heap_copytuple(tuple);
+	return false;
+}
 
-	heap_deform_tuple(tuple, oldTupDesc, values, isnull);
+/*
+ * Subroutine for reform_and_rewrite_tuple and heap_insert_for_repack.
+ *
+ * Set values of dropped columns to NULL,
+ */
+static void
+clear_dropped_attributes(HeapTuple tuple, TupleTableSlot *reform)
+{
+	TupleDesc	tupDesc = reform->tts_tupleDescriptor;
+
+	/* Assuming 'reform' is virtual, this deforms the tuple. */
+	Assert(TTS_IS_VIRTUAL(reform));
+	ExecForceStoreHeapTuple(tuple, reform, false);
 
-	for (int i = 0; i < newTupDesc->natts; i++)
+	for (int i = 0; i < tupDesc->natts; i++)
 	{
-		if (TupleDescCompactAttr(newTupDesc, i)->attisdropped)
-			isnull[i] = true;
+		if (TupleDescCompactAttr(tupDesc, i)->attisdropped)
+			reform->tts_isnull[i] = true;
 	}
-
-	return heap_form_tuple(newTupDesc, values, isnull);
 }
 
 /*
-- 
2.52.0


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v01-0002-Move-functions-to-repack.c.patch



^ permalink  raw  reply  [nested|flat] 220+ messages in thread