agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v17 2/8] Row pattern recognition patch (parse/analysis).
188+ messages / 2 participants
[nested] [flat]

* [PATCH v17 2/8] Row pattern recognition patch (parse/analysis).
@ 2024-04-28 11:00 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

From: Tatsuo Ishii @ 2024-04-28 11:00 UTC (permalink / raw)

---
 src/backend/parser/parse_agg.c    |   7 +
 src/backend/parser/parse_clause.c | 296 +++++++++++++++++++++++++++++-
 src/backend/parser/parse_expr.c   |   4 +
 src/backend/parser/parse_func.c   |   3 +
 4 files changed, 309 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 4fc5fc87e0..003a1e14ce 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->runCondition = NIL;
 		wc->winref = winref;
 
@@ -3821,3 +3832,286 @@ 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 1c1c86aa3e..5540a0fb0a 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -578,6 +578,7 @@ 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;
 
@@ -1817,6 +1818,7 @@ transformSubLink(ParseState *pstate, SubLink *sublink)
 		case EXPR_KIND_VALUES:
 		case EXPR_KIND_VALUES_SINGLE:
 		case EXPR_KIND_CYCLE_MARK:
+		case EXPR_KIND_RPR_DEFINE:
 			/* okay */
 			break;
 		case EXPR_KIND_CHECK_CONSTRAINT:
@@ -3197,6 +3199,8 @@ 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 0cbc950c95..ad982a7c17 100644
--- a/src/backend/parser/parse_func.c
+++ b/src/backend/parser/parse_func.c
@@ -2657,6 +2657,9 @@ 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(Sun_Apr_28_20_28_26_2024_444)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v17-0003-Row-pattern-recognition-patch-rewriter.patch"



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread

* [PATCH v47 4/9] repack code cleanups
@ 2026-03-31 14:48 Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 188+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 188+ messages in thread