agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v30 03/11] Allow to prolong life span of transition tables until transaction end
360+ messages / 2 participants
[nested] [flat]

* [PATCH v30 03/11] Allow to prolong life span of transition tables until transaction end
@ 2019-12-20 01:09  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

From: Yugo Nagata @ 2019-12-20 01:09 UTC (permalink / raw)

Originally, tuplestores of AFTER trigger's transition tables were
freed for each query depth. For our IVM implementation, we would like
to prolong life of the tuplestores because we have to preserve them
for a whole query assuming that some base tables might be changed
in some trigger functions.
---
 src/backend/commands/trigger.c | 83 ++++++++++++++++++++++++++++++++--
 src/include/commands/trigger.h |  2 +
 2 files changed, 81 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index c344ff0944..364e3a53f7 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -3761,6 +3761,10 @@ typedef struct AfterTriggerEventList
  * end of the list, so it is relatively easy to discard them.  The event
  * list chunks themselves are stored in event_cxt.
  *
+ * prolonged_tuplestored is a list of transition table tuplestores whose
+ * life are prolonged to the end of the outmost query instead of each nested
+ * query.
+ *
  * query_depth is the current depth of nested AfterTriggerBeginQuery calls
  * (-1 when the stack is empty).
  *
@@ -3826,6 +3830,7 @@ typedef struct AfterTriggersData
 	SetConstraintState state;	/* the active S C state */
 	AfterTriggerEventList events;	/* deferred-event list */
 	MemoryContext event_cxt;	/* memory context for events, if any */
+	List   *prolonged_tuplestores;	/* list of prolonged tuplestores */
 
 	/* per-query-level data: */
 	AfterTriggersQueryData *query_stack;	/* array of structs shown below */
@@ -3861,6 +3866,7 @@ struct AfterTriggersTableData
 	bool		closed;			/* true when no longer OK to add tuples */
 	bool		before_trig_done;	/* did we already queue BS triggers? */
 	bool		after_trig_done;	/* did we already queue AS triggers? */
+	bool		prolonged;			/* are transition tables prolonged? */
 	AfterTriggerEventList after_trig_events;	/* if so, saved list pointer */
 
 	/*
@@ -3910,6 +3916,7 @@ static void TransitionTableAddTuple(EState *estate,
 									TupleTableSlot *original_insert_tuple,
 									Tuplestorestate *tuplestore);
 static void AfterTriggerFreeQuery(AfterTriggersQueryData *qs);
+static void release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged);
 static SetConstraintState SetConstraintStateCreate(int numalloc);
 static SetConstraintState SetConstraintStateCopy(SetConstraintState origstate);
 static SetConstraintState SetConstraintStateAddItem(SetConstraintState state,
@@ -4787,6 +4794,45 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 }
 
 
+/*
+ * SetTransitionTablePreserved
+ *
+ * Prolong lifespan of transition tables corresponding specified relid and
+ * command type to the end of the outmost query instead of each nested query.
+ * This enables to use nested AFTER trigger's transition tables from outer
+ * query's triggers.  Currently, only immediate incremental view maintenance
+ * uses this.
+ */
+void
+SetTransitionTablePreserved(Oid relid, CmdType cmdType)
+{
+	AfterTriggersTableData *table;
+	AfterTriggersQueryData *qs;
+	bool		found = false;
+	ListCell   *lc;
+
+	/* Check state, like AfterTriggerSaveEvent. */
+	if (afterTriggers.query_depth < 0)
+		elog(ERROR, "SetTransitionTablePreserved() called outside of query");
+
+	qs = &afterTriggers.query_stack[afterTriggers.query_depth];
+
+	foreach(lc, qs->tables)
+	{
+		table = (AfterTriggersTableData *) lfirst(lc);
+		if (table->relid == relid && table->cmdType == cmdType &&
+			table->closed)
+		{
+			table->prolonged = true;
+			found = true;
+		}
+	}
+
+	if (!found)
+		elog(ERROR,"could not find table with OID %d and command type %d", relid, cmdType);
+}
+
+
 /*
  * GetAfterTriggersTableData
  *
@@ -4997,6 +5043,7 @@ AfterTriggerBeginXact(void)
 	 */
 	afterTriggers.firing_counter = (CommandId) 1;	/* mustn't be 0 */
 	afterTriggers.query_depth = -1;
+	afterTriggers.prolonged_tuplestores = NIL;
 
 	/*
 	 * Verify that there is no leftover state remaining.  If these assertions
@@ -5157,19 +5204,19 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 		ts = table->old_upd_tuplestore;
 		table->old_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_upd_tuplestore;
 		table->new_upd_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->old_del_tuplestore;
 		table->old_del_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		ts = table->new_ins_tuplestore;
 		table->new_ins_tuplestore = NULL;
 		if (ts)
-			tuplestore_end(ts);
+			release_or_prolong_tuplestore(ts, table->prolonged);
 		if (table->storeslot)
 		{
 			TupleTableSlot *slot = table->storeslot;
@@ -5186,6 +5233,34 @@ AfterTriggerFreeQuery(AfterTriggersQueryData *qs)
 	 */
 	qs->tables = NIL;
 	list_free_deep(tables);
+
+	/* Release prolonged tuplestores at the end of the outmost query */
+	if (afterTriggers.query_depth == 0)
+	{
+		foreach(lc, afterTriggers.prolonged_tuplestores)
+		{
+			ts = (Tuplestorestate *) lfirst(lc);
+			if (ts)
+				tuplestore_end(ts);
+		}
+		afterTriggers.prolonged_tuplestores = NIL;
+	}
+}
+
+/*
+ * Release the tuplestore, or append it to the prolonged tuplestores list.
+ */
+static void
+release_or_prolong_tuplestore(Tuplestorestate *ts, bool prolonged)
+{
+	if (prolonged && afterTriggers.query_depth > 0)
+	{
+		MemoryContext oldcxt = MemoryContextSwitchTo(CurTransactionContext);
+		afterTriggers.prolonged_tuplestores = lappend(afterTriggers.prolonged_tuplestores, ts);
+		MemoryContextSwitchTo(oldcxt);
+	}
+	else
+		tuplestore_end(ts);
 }
 
 
diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h
index 8a5a9fe642..6718514d34 100644
--- a/src/include/commands/trigger.h
+++ b/src/include/commands/trigger.h
@@ -265,6 +265,8 @@ extern void AfterTriggerEndSubXact(bool isCommit);
 extern void AfterTriggerSetState(ConstraintsSetStmt *stmt);
 extern bool AfterTriggerPendingOnRel(Oid relid);
 
+extern void SetTransitionTablePreserved(Oid relid, CmdType cmdType);
+
 
 /*
  * in utils/adt/ri_triggers.c
-- 
2.25.1


--Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt
Content-Type: text/x-diff;
 name="v30-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Disposition: attachment;
 filename="v30-0004-Add-Incremental-View-Maintenance-support-to-pg_d.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 360+ messages in thread

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

So far, the relfrozenxid and relminmxid attributes of pg_class used to be
updated by swap_relation_files(), however, not every call of the function
should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will
need to update this information in one case that would be tricky to handle
using swap_relation_files().
---
 src/backend/commands/repack.c | 114 +++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 58 deletions(-)

diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c
index 6f3e4ecff46..92c1b678e6f 100644
--- a/src/backend/commands/repack.c
+++ b/src/backend/commands/repack.c
@@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti,
 							ChangeContext *chgcxt);
+static void update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+									MultiXactId cutoffMulti);
 static List *get_tables_to_repack(RepackCommand cmd, bool usingindex,
 								  MemoryContext permcxt);
 static List *get_tables_to_repack_partitioned(RepackCommand cmd,
@@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex,
  * links) while the latter is the only way to handle cases in which a toast
  * table is added or removed altogether.
  *
- * Additionally, the first relation is marked with relfrozenxid set to
- * frozenXid.  It seems a bit ugly to have this here, but the caller would
- * have to do it anyway, so having it here saves a heap_update.  Note: in
- * the swap-toast-links case, we assume we don't need to change the toast
- * table's relfrozenxid: the new version of the toast table should already
- * have relfrozenxid set to RecentXmin, which is good enough.
- *
  * Lastly, if r2 and its toast table and toast index (if any) are mapped,
  * their OIDs are emitted into mapped_tables[].  This is hacky but beats
  * having to look the information up again later in finish_heap_swap.
@@ -2029,9 +2024,7 @@ static void
 swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 					bool swap_toast_by_content,
 					bool is_internal,
-					TransactionId frozenXid,
-					MultiXactId cutoffMulti,
-					Oid *mapped_tables)
+					Oid *mapped_tables, Oid *r1_toastid)
 {
 	Relation	relRelation;
 	HeapTuple	reltup1,
@@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	relam1 = relform1->relam;
 	relam2 = relform2->relam;
 
+	if (r1_toastid)
+		*r1_toastid = relform1->reltoastrelid;
+
 	if (RelFileNumberIsValid(relfilenumber1) &&
 		RelFileNumberIsValid(relfilenumber2))
 	{
@@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	 * and then fail to commit the pg_class update.
 	 */
 
-	/* set rel1's frozen Xid and minimum MultiXid */
-	if (relform1->relkind != RELKIND_INDEX)
-	{
-		Assert(!TransactionIdIsValid(frozenXid) ||
-			   TransactionIdIsNormal(frozenXid));
-		relform1->relfrozenxid = frozenXid;
-		relform1->relminmxid = cutoffMulti;
-	}
-
 	/* swap size statistics too, since new rel has freshly-updated stats */
 	{
 		int32		swap_pages;
@@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 									target_is_pg_class,
 									swap_toast_by_content,
 									is_internal,
-									frozenXid,
-									cutoffMulti,
-									mapped_tables);
+									mapped_tables,
+									NULL);
 			}
 			else
 			{
@@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 							target_is_pg_class,
 							swap_toast_by_content,
 							is_internal,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 	}
 
 	/* Clean up. */
@@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class,
 	table_close(relRelation, RowExclusiveLock);
 }
 
+/*
+ * Update relfrozenxid and relminmxid attributes of pg_class entry, specified
+ * by OID.
+ */
+static void
+update_relation_cutoffs(Oid relid, TransactionId frozenXid,
+						MultiXactId cutoffMulti)
+{
+	Relation	relRelation;
+	HeapTuple	reltup;
+	Form_pg_class relform;
+	CatalogIndexState indstate;
+
+	relRelation = table_open(RelationRelationId, RowExclusiveLock);
+	reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
+	if (!HeapTupleIsValid(reltup))
+		elog(ERROR, "cache lookup failed for relation %u", relid);
+	relform = (Form_pg_class) GETSTRUCT(reltup);
+	relform->relfrozenxid = frozenXid;
+	relform->relminmxid = cutoffMulti;
+
+	indstate = CatalogOpenIndexes(relRelation);
+	CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup,
+							   indstate);
+	CatalogCloseIndexes(indstate);
+
+	heap_freetuple(reltup);
+	table_close(relRelation, RowExclusiveLock);
+}
+
 /*
  * Remove the transient table that was built by make_new_heap, and finish
  * cleaning up (including rebuilding all indexes on the old heap).
@@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 {
 	ObjectAddress object;
 	Oid			mapped_tables[4];
+	Oid			oid_old_toastid;
 	int			i;
 
 	/* Report that we are now swapping relation files */
@@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 	swap_relation_files(OIDOldHeap, OIDNewHeap,
 						(OIDOldHeap == RelationRelationId),
 						swap_toast_by_content, is_internal,
-						frozenXid, cutoffMulti, mapped_tables);
+						mapped_tables, &oid_old_toastid);
 
 	/*
 	 * If it's a system catalog, queue a sinval message to flush all catcaches
@@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap,
 								 PROGRESS_REPACK_PHASE_FINAL_CLEANUP);
 
 	/*
-	 * If the relation being rebuilt is pg_class, swap_relation_files()
-	 * couldn't update pg_class's own pg_class entry (check comments in
-	 * swap_relation_files()), thus relfrozenxid was not updated. That's
-	 * annoying because a potential reason for doing a VACUUM FULL is a
-	 * imminent or actual anti-wraparound shutdown.  So, now that we can
-	 * access the new relation using its indices, update relfrozenxid.
-	 * pg_class doesn't have a toast relation, so we don't need to update the
-	 * corresponding toast relation. Not that there's little point moving all
-	 * relfrozenxid updates here since swap_relation_files() needs to write to
-	 * pg_class for non-mapped relations anyway.
+	 * Update relfrozenxid and relminmxid. CCI is needed to see the most
+	 * recent pg_class tuple, created by swap_relation_files(). However that
+	 * CCI makes us use the new relation file. Therefore we cannot do this
+	 * before indexes have been rebuilt too.
 	 */
-	if (OIDOldHeap == RelationRelationId)
-	{
-		Relation	relRelation;
-		HeapTuple	reltup;
-		Form_pg_class relform;
-
-		relRelation = table_open(RelationRelationId, RowExclusiveLock);
-
-		reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap));
-		if (!HeapTupleIsValid(reltup))
-			elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap);
-		relform = (Form_pg_class) GETSTRUCT(reltup);
-
-		relform->relfrozenxid = frozenXid;
-		relform->relminmxid = cutoffMulti;
-
-		CatalogTupleUpdate(relRelation, &reltup->t_self, reltup);
+	CommandCounterIncrement();
+	update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti);
 
-		table_close(relRelation, RowExclusiveLock);
-	}
+	/*
+	 * The same for TOAST, if needed. In the swap-toast-links case, the new
+	 * the toast table should already have relfrozenxid set to RecentXmin.
+	 */
+	if (OidIsValid(oid_old_toastid) && swap_toast_by_content)
+		update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti);
 
 	/* Destroy new heap with old filenumber */
 	object.classId = RelationRelationId;
@@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap,
 							(old_table_oid == RelationRelationId),
 							false,	/* swap_toast_by_content */
 							true,
-							InvalidTransactionId,
-							InvalidMultiXactId,
-							mapped_tables);
+							mapped_tables,
+							NULL);
 
 #ifdef USE_ASSERT_CHECKING
 
-- 
2.52.0


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch



^ permalink  raw  reply  [nested|flat] 360+ messages in thread