agora inbox for pgsql-hackers@postgresql.org  

help / color / mirror / Atom feed

[PATCH v1 1/1] remove pg_spin_delay()
604+ messages / 2 participants
[nested] [flat]

* [PATCH v1 1/1] remove pg_spin_delay()
@ 2026-05-05 17:37 Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 604+ messages in thread

From: Nathan Bossart @ 2026-05-05 17:37 UTC (permalink / raw)

---
 src/include/port/atomics.h          |  5 ---
 src/include/port/atomics/arch-x86.h | 54 -----------------------------
 src/include/port/atomics/generic.h  |  6 ----
 3 files changed, 65 deletions(-)

diff --git a/src/include/port/atomics.h b/src/include/port/atomics.h
index d8b1d20fe60..c50d95d29e2 100644
--- a/src/include/port/atomics.h
+++ b/src/include/port/atomics.h
@@ -154,11 +154,6 @@
 #define pg_read_barrier()	pg_read_barrier_impl()
 #define pg_write_barrier()	pg_write_barrier_impl()
 
-/*
- * Spinloop delay - Allow CPU to relax in busy loops
- */
-#define pg_spin_delay() pg_spin_delay_impl()
-
 /*
  * pg_atomic_init_flag - initialize atomic flag.
  *
diff --git a/src/include/port/atomics/arch-x86.h b/src/include/port/atomics/arch-x86.h
index bd6f4f56ca2..b317cf7a188 100644
--- a/src/include/port/atomics/arch-x86.h
+++ b/src/include/port/atomics/arch-x86.h
@@ -76,60 +76,6 @@ typedef struct pg_atomic_uint64
 } pg_atomic_uint64;
 #endif	/* __x86_64__ */
 
-#endif /* defined(__GNUC__) || defined(__INTEL_COMPILER) */
-
-#if !defined(PG_HAVE_SPIN_DELAY)
-/*
- * This sequence is equivalent to the PAUSE instruction ("rep" is
- * ignored by old IA32 processors if the following instruction is
- * not a string operation); the IA-32 Architecture Software
- * Developer's Manual, Vol. 3, Section 7.7.2 describes why using
- * PAUSE in the inner loop of a spin lock is necessary for good
- * performance:
- *
- *     The PAUSE instruction improves the performance of IA-32
- *     processors supporting Hyper-Threading Technology when
- *     executing spin-wait loops and other routines where one
- *     thread is accessing a shared lock or semaphore in a tight
- *     polling loop. When executing a spin-wait loop, the
- *     processor can suffer a severe performance penalty when
- *     exiting the loop because it detects a possible memory order
- *     violation and flushes the core processor's pipeline. The
- *     PAUSE instruction provides a hint to the processor that the
- *     code sequence is a spin-wait loop. The processor uses this
- *     hint to avoid the memory order violation and prevent the
- *     pipeline flush. In addition, the PAUSE instruction
- *     de-pipelines the spin-wait loop to prevent it from
- *     consuming execution resources excessively.
- */
-#if defined(__GNUC__) || defined(__INTEL_COMPILER)
-#define PG_HAVE_SPIN_DELAY
-static inline void
-pg_spin_delay_impl(void)
-{
-	__asm__ __volatile__(" rep; nop			\n");
-}
-#elif defined(_MSC_VER) && defined(__x86_64__)
-#define PG_HAVE_SPIN_DELAY
-static __forceinline void
-pg_spin_delay_impl(void)
-{
-	_mm_pause();
-}
-#elif defined(_MSC_VER)
-#define PG_HAVE_SPIN_DELAY
-static __forceinline void
-pg_spin_delay_impl(void)
-{
-	/* See comment for gcc code. Same code, MASM syntax */
-	__asm rep nop;
-}
-#endif
-#endif /* !defined(PG_HAVE_SPIN_DELAY) */
-
-
-#if defined(__GNUC__) || defined(__INTEL_COMPILER)
-
 #define PG_HAVE_ATOMIC_TEST_SET_FLAG
 static inline bool
 pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr)
diff --git a/src/include/port/atomics/generic.h b/src/include/port/atomics/generic.h
index fd64b6cbd86..daa772e9a6d 100644
--- a/src/include/port/atomics/generic.h
+++ b/src/include/port/atomics/generic.h
@@ -28,12 +28,6 @@
 #	define pg_write_barrier_impl pg_memory_barrier_impl
 #endif
 
-#ifndef PG_HAVE_SPIN_DELAY
-#define PG_HAVE_SPIN_DELAY
-#define pg_spin_delay_impl()	((void)0)
-#endif
-
-
 /* provide fallback */
 #if !defined(PG_HAVE_ATOMIC_FLAG_SUPPORT) && defined(PG_HAVE_ATOMIC_U32_SUPPORT)
 #define PG_HAVE_ATOMIC_FLAG_SUPPORT
-- 
2.50.1 (Apple Git-155)


--9wPlq30DMLxbhZ5y--





^ permalink  raw  reply  [nested|flat] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread

* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files().
@ 2026-06-16 11:54 Antonin Houska <ah@cybertec.at>
  0 siblings, 0 replies; 604+ 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] 604+ messages in thread